© 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. 17-GEMMASCOPE-RES-16K
    11. 872
    Prev
    Next
    INDEX
    Explanations

    references to locations or positions within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.66
     препратки
    -0.59
     sooner
    -0.51
    tedly
    -0.50
     Mexicano
    -0.48
    SOUNDBITE
    -0.47
    lateur
    -0.47
    narrow
    -0.46
    ゴン
    -0.46
     accordingly
    -0.46
    POSITIVE LOGITS
    IsMutable
    0.81
    ReusableCell
    0.77
    TintMode
    0.74
    AnchorStyles
    0.73
    featureID
    0.72
    AccessorTable
    0.69
    )");
    0.68
    }")
    0.64
    WebServlet
    0.64
    DockStyle
    0.63
    Activations Density 0.068%

    No Known Activations