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

    Neuronpedia

    Jacobian LensNEW
    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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102873
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and coding constructs

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

    Programming, scientific, or markup language tokens that represent either specialized technical terminology or functional elements in code/HTML/XML documents.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    elemField
    -0.55
     насељу
    -0.55
    __*/
    -0.54
    webElementXpaths
    -0.53
     يتيمه
    -0.51
     Numerade
    -0.50
    RefNanny
    -0.50
     مشين
    -0.50
    RTGC
    -0.50
     SwitchCompat
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.44
     datasource
    0.40
    .*")]
    0.38
    Pop
    0.38
     Pop
    0.37
     kasarigan
    0.37
     panning
    0.37
    抱
    0.36
    Aix
    0.36
     صح
    0.35
    Activations Density 0.200%

    No Known Activations