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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 756
    Prev
    Next
    INDEX
    Explanations

    mentions of filesystem-related functions and modules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.62
     Tartar
    -0.62
     NSCoder
    -0.61
     neutre
    -0.60
    TagHelper
    -0.60
    smithy
    -0.60
    eachtet
    -0.58
     solstice
    -0.58
     Laplacian
    -0.58
     marinho
    -0.58
    POSITIVE LOGITS
    fs
    1.15
     os
    1.08
     fs
    1.02
    DoubleQuotes
    0.93
    FS
    0.86
     Os
    0.73
    migrationBuilder
    0.73
    HtmlAttribute
    0.70
    WriteTagHelper
    0.69
    yarnpkg
    0.67
    Activations Density 0.067%

    No Known Activations