© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 13045
    Prev
    Next
    INDEX
    Explanations

    elements and objects that are part of a programming interface or user interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.56
    balleur
    -0.55
    DrawerLayout
    -0.53
    UrlResolution
    -0.52
    CharStream
    -0.46
    rouvez
    -0.46
     bieber
    -0.46
    ارد
    -0.45
    щадь
    -0.45
    ntz
    -0.45
    POSITIVE LOGITS
    jspx
    5.77
    ftagPool
    1.75
    WireFormatLite
    1.02
    SourceChecksum
    1.00
     jspb
    0.80
    ScopeManager
    0.77
    adaptiveStyles
    0.77
    клопе
    0.76
    tagext
    0.74
    providedIn
    0.74
    Activations Density 0.003%

    No Known Activations