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. 0-GEMMASCOPE-RES-16K
    6. 7019
    Prev
    Next
    INDEX
    Explanations

    technical terms and programming-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upyter
    -0.46
     or
    -0.41
    cplusplus
    -0.41
    grunns
    -0.40
    attenzione
    -0.39
     \/
    -0.38
     Alfa
    -0.38
     gong
    -0.38
    Alfa
    -0.38
    applicazione
    -0.38
    POSITIVE LOGITS
    DockStyle
    1.01
     intptr
    1.00
     AssemblyCulture
    0.91
     estekak
    0.91
    ISupport
    0.88
    migrationBuilder
    0.81
    >//
    0.80
    uxxxx
    0.79
    IntoConstraints
    0.77
    AnchorStyles
    0.76
    Activations Density 2.368%

    No Known Activations