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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 6286
    Prev
    Next
    INDEX
    Explanations

    concepts related to technology and its applications in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.37
     оригіналу
    -0.36
     مترجم
    -0.33
    AutoScaleMode
    -0.31
    <_>
    -0.30
     combineReducers
    -0.30
    ıştı
    -0.29
    chuga
    -0.29
     AttributeSet
    -0.29
     Happened
    -0.29
    POSITIVE LOGITS
     plays
    2.69
     play
    2.61
     played
    2.41
     Plays
    2.23
    plays
    2.23
     playing
    2.19
     PLAY
    2.06
    Plays
    2.06
    play
    2.05
    played
    2.05
    Activations Density 1.334%

    No Known Activations