Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13314
    Prev
    Next
    INDEX
    Explanations

    terminologies and structures related to data lifecycle management in a programming or data handling context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.65
    expandindo
    -0.53
    IsMutable
    -0.48
    ThroughAttribute
    -0.46
     invokingState
    -0.43
    berdayakan
    -0.40
     препратки
    -0.40
     Numerade
    -0.38
     ✭✭
    -0.38
     lenker
    -0.36
    POSITIVE LOGITS
    rungsseite
    0.57
     tardi
    0.50
     Infórmanos
    0.47
    Myr
    0.46
     MainAxisSize
    0.45
     insuffisamment
    0.44
    stande
    0.44
    IntoConstraints
    0.44
     EARL
    0.43
    ChildScrollView
    0.42
    Activations Density 0.654%

    No Known Activations