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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 6826
    Prev
    Next
    INDEX
    Explanations

    terms related to coding, configuration, and data transfer in computer systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     legado
    -0.44
    TypedDataSet
    -0.40
     frenos
    -0.38
     anciennes
    -0.37
     anciens
    -0.37
    ScopeManager
    -0.36
     antichi
    -0.36
     marinho
    -0.34
    Career
    -0.34
     legacy
    -0.34
    POSITIVE LOGITS
     &___
    0.63
     Infórmanos
    0.60
     surla
    0.59
    matchCondition
    0.59
    Diweddarwch
    0.57
    ftagPool
    0.56
    icitis
    0.55
     Biôgrafia
    0.54
     BufferedWriter
    0.53
    yarnpkg
    0.53
    Activations Density 2.776%

    No Known Activations