© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15948
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to specific locations or physical areas within text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    references to specific subregions or subsets within a larger whole, often expressed in prepositional phrases (e.g., region/area/scale/group/strata).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    technical or scientific text discussing specific locations, regions, or areas within a system or structure.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.53
    InjectAttribute
    -0.46
    Personendaten
    -0.43
     '\\;'
    -0.42
    各样的
    -0.42
    united
    -0.41
    يكب
    -0.40
    LabelTagHelper
    -0.39
    nities
    -0.39
    rrggbb
    -0.38
    POSITIVE LOGITS
     especially
    0.58
    especially
    0.54
     zwłaszcza
    0.48
    Especially
    0.46
     particularly
    0.46
     khususnya
    0.46
     besonders
    0.46
    尤其是
    0.45
     особенно
    0.45
    particularly
    0.45
    Activations Density 0.588%

    No Known Activations