© 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. 16160
    Prev
    Next
    INDEX
    Explanations

    occurrences of copyright symbols and related notations

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

    copyright and license headers in source code files.

    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
     nahilalakip
    -0.58
     Infórmanos
    -0.56
     EconPapers
    -0.54
    fjspx
    -0.53
     ब्रेकडाउन
    -0.52
    IVEREF
    -0.47
     HasFactory
    -0.47
    ContentAsync
    -0.47
    mybatisplus
    -0.45
     AppCompatTheme
    -0.45
    POSITIVE LOGITS
    entyfik
    0.42
     Helden
    0.40
    ckså
    0.39
    C
    0.37
    znám
    0.37
     refine
    0.37
     revisión
    0.34
    S
    0.34
    覚えて
    0.34
     maravillas
    0.34
    Activations Density 1.109%

    No Known Activations