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. 10-GEMMASCOPE-RES-16K
    6. 7432
    Prev
    Next
    INDEX
    Explanations

    symbols related to currency and data formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FirebaseDatabase
    -0.38
    bigsqcup
    -0.32
    tidase
    -0.32
    binaan
    -0.32
     Савезне
    -0.31
    wantErr
    -0.31
     new
    -0.28
     hemsida
    -0.28
    ">//
    -0.27
     heureuse
    -0.27
    POSITIVE LOGITS
    DispatchToProps
    0.67
    AddTagHelper
    0.67
    IntoConstraints
    0.61
    MLLoader
    0.61
    XtraReports
    0.60
    StoryboardSegue
    0.57
     nakalista
    0.56
    AccessorTable
    0.55
    subs
    0.54
    BagConstraints
    0.54
    Activations Density 0.413%

    No Known Activations