Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7431
    Prev
    Next
    INDEX
    Explanations

    references to product specifications and releases

    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
    UrlResolution
    -0.75
    RenderAtEndOf
    -0.70
     surla
    -0.65
    ftagPool
    -0.59
    principalColumn
    -0.58
    ChildScrollView
    -0.56
    脚注の使い方
    -0.55
    ViewFeatures
    -0.54
     noDo
    -0.54
    AndEndTag
    -0.53
    POSITIVE LOGITS
    viewDid
    0.54
     Occup
    0.53
     iPad
    0.43
    Occup
    0.43
     Kinect
    0.38
     Paese
    0.36
    陽
    0.35
     Facebook
    0.35
     tasar
    0.35
     Skyrim
    0.34
    Activations Density 0.489%

    No Known Activations