© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 82934
    Prev
    Next
    INDEX
    Explanations

    elements of personal growth and self-awareness

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

    learned a great deal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iserie
    -0.44
    styleType
    -0.41
    DebuggerNonUser
    -0.38
     BorderSide
    -0.38
    FromNib
    -0.38
    LookAnd
    -0.38
    ResumeLayout
    -0.38
    RenderAtEndOf
    -0.35
     Maz
    -0.34
    Enlaces
    -0.34
    POSITIVE LOGITS
     learn
    2.39
     learns
    2.20
     learned
    2.16
     Learn
    2.11
    Learn
    2.09
    learn
    2.09
     learnt
    2.03
     aprender
    1.99
     learning
    1.96
     LEARN
    1.87
    Activations Density 0.109%

    No Known Activations