© 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. 7367
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to hardware functionalities and capabilities

    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
    multicolumn
    -0.34
    申
    -0.31
     Outside
    -0.31
     fen
    -0.31
     domin
    -0.31
     Tol
    -0.30
    Obrázky
    -0.30
    qxd
    -0.30
     Mez
    -0.30
     Bock
    -0.29
    POSITIVE LOGITS
     built
    2.38
    built
    2.11
     Built
    2.05
    Built
    2.05
     builtin
    2.00
     BUILT
    1.91
    内置
    1.83
     встроен
    1.73
    BUILT
    1.73
    builtin
    1.59
    Activations Density 0.719%

    No Known Activations