© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2219
    Prev
    Next
    INDEX
    Explanations

    terms related to coding structures and specifications, particularly in programming and audio session management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    Coordonnées
    -0.53
    gdala
    -0.52
    TypedDataSet
    -0.51
     муніципалі
    -0.50
     ControllerBase
    -0.49
    EndGlobalSection
    -0.48
     AssemblyCompany
    -0.48
    цията
    -0.47
    IMON
    -0.46
    toli
    -0.46
    POSITIVE LOGITS
    DockStyle
    1.17
     FetchType
    1.10
    FetchType
    0.97
    GenerationType
    0.82
     Мексичка
    0.79
     GenerationType
    0.75
    WindowConstants
    0.73
    extAlignment
    0.71
    TemporalType
    0.71
     TimeUnit
    0.70
    Activations Density 0.263%

    No Known Activations