© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 16037
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those associated with statistics or legal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.65
     HasFactory
    -0.61
    errHandler
    -0.61
     للاسماء
    -0.60
     initComponents
    -0.59
    writeFieldEnd
    -0.59
    twimg
    -0.59
    ViewFeatures
    -0.59
    AnimationsModule
    -0.57
     typelib
    -0.57
    POSITIVE LOGITS
     Tig
    0.33
     Sig
    0.32
    Tig
    0.32
     torch
    0.32
    Sig
    0.32
    setConfig
    0.31
     skolen
    0.31
     Details
    0.31
     πλη
    0.30
     bekym
    0.29
    Activations Density 0.713%

    No Known Activations