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. 8-GEMMASCOPE-RES-16K
    6. 8728
    Prev
    Next
    INDEX
    Explanations

    references to the "goog" library and its associated components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    RenderAtEndOf
    -0.85
    setDo
    -0.73
     ProtoMessage
    -0.72
     يتيمه
    -0.72
    localctx
    -0.70
     kasarigan
    -0.70
    DebuggerNonUser
    -0.68
    Hauptartikel
    -0.67
    Tikang
    -0.67
    !*\
    -0.66
    POSITIVE LOGITS
    cshtml
    2.01
    awtextra
    1.34
    setBounds
    0.96
    NullCheck
    0.84
    BagConstraints
    0.77
    protoc
    0.75
    fastjson
    0.61
    URIComponent
    0.61
    MIDDLEWARE
    0.60
     autorytatywna
    0.59
    Activations Density 0.047%

    No Known Activations