© 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. 2-GEMMASCOPE-RES-16K
    6. 844
    Prev
    Next
    INDEX
    Explanations

    programming-related operations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.58
    tvguidetime
    -0.58
     '@/
    -0.54
    ValueStyle
    -0.54
     Wiktionnaire
    -0.52
    insee
    -0.51
    󠁴
    -0.50
     pengh
    -0.50
    expandindo
    -0.50
    ("$.
    -0.49
    POSITIVE LOGITS
    ImageContext
    0.97
     BoxDecoration
    0.82
    ReusableCell
    0.78
    posedge
    0.77
     resourceCulture
    0.76
    ConstraintMaker
    0.76
     useCallback
    0.73
    mergeFrom
    0.72
     createContext
    0.71
    RectangleBorder
    0.70
    Activations Density 0.595%

    No Known Activations