© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3341
    Prev
    Next
    INDEX
    Explanations

    clarifications and references to specific details or conditions in documents

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

    phrases beginning with "For the" that introduce explanations or reasons.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    principalTable
    -0.56
    expandindo
    -0.54
    astéroïdes
    -0.53
     виправивши
    -0.52
    PARATUS
    -0.49
    ParseTree
    -0.47
    czer
    -0.47
    購入した
    -0.47
    TestingModule
    -0.45
    coltà
    -0.45
    POSITIVE LOGITS
     purposes
    1.73
     sake
    1.40
    purposes
    1.28
     Purposes
    1.24
     purpose
    1.13
     reasons
    1.06
     Zwecke
    0.88
    purpose
    0.85
    reasons
    0.83
    来说
    0.81
    Activations Density 0.731%

    No Known Activations