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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15118
    Prev
    Next
    INDEX
    Explanations

    codes related to user interface elements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     makeStyles
    -0.68
     Panto
    -0.63
     NgModule
    -0.60
     Dut
    -0.59
    conducting
    -0.59
    NgModule
    -0.58
    styleType
    -0.58
    FOTO
    -0.56
    ʺ
    -0.56
    toggler
    -0.55
    POSITIVE LOGITS
    ValueStyle
    1.00
     cref
    0.97
    SharedCtor
    0.96
    ReusableCell
    0.93
     propOrder
    0.89
     createState
    0.86
     typelib
    0.81
    RenderAtEndOf
    0.81
    webpack
    0.78
    PerformLayout
    0.76
    Activations Density 0.006%

    No Known Activations