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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14274
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their properties or interactions

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

    scientific table formatting in research papers with numerical data, citations, and chemical/biological terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     мәкал
    -0.62
    AddTagHelper
    -0.60
    CloseOperation
    -0.56
    تقاوى
    -0.53
     createSlice
    -0.52
    IVEREF
    -0.52
     typelib
    -0.52
    +#+#
    -0.49
    TagMode
    -0.48
    انجليز
    -0.47
    POSITIVE LOGITS
     Hälfte
    0.41
     franchise
    0.38
     track
    0.35
     semula
    0.35
     loudest
    0.35
     majority
    0.34
    no
    0.34
     
    0.34
    endaftaran
    0.34
     outdated
    0.33
    Activations Density 1.787%

    No Known Activations