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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 367
    Prev
    Next
    INDEX
    Explanations

    documentation comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ControllerBase
    -0.47
    transQ
    -0.46
     resourceCulture
    -0.46
    CGRectMake
    -0.45
    oa̍t
    -0.45
    cookieParser
    -0.44
    tinyos
    -0.43
    memoized
    -0.43
     affic
    -0.40
    PushButton
    -0.39
    POSITIVE LOGITS
     @
    0.56
     Chwiliwch
    0.51
    parametrize
    0.51
     تضيفلها
    0.50
     invokingState
    0.50
    XmlAccessType
    0.47
    ValueStyle
    0.46
     hawk
    0.45
    gdala
    0.45
     الحره
    0.44
    Activations Density 0.053%

    No Known Activations