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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14398
    Prev
    Next
    INDEX
    Explanations

    technical jargon and terminology related to engineering and electronics

    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
    LElement
    -0.34
    rif
    -0.32
     {})
    -0.30
    mulos
    -0.29
    ={`${
    -0.29
    "",
    -0.28
    {})
    -0.27
    tened
    -0.27
    =[];
    -0.27
    ParseTree
    -0.27
    POSITIVE LOGITS
     applications
    1.21
     Anwendungen
    1.16
    applications
    1.02
     aplicaciones
    1.01
     Applications
    1.01
    Applications
    0.99
     APPLICATIONS
    0.94
     applicazioni
    0.94
    APPLICATIONS
    0.93
     situations
    0.88
    Activations Density 1.115%

    No Known Activations