© 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. 16-GEMMASCOPE-RES-16K
    11. 4761
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare systems and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "from" or "system"

    np_acts-logits-general · gemini-2.0-flash

    domains of life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "{\
    -0.53
    setContentView
    -0.49
    </h5>
    -0.49
    WindowConstants
    -0.48
    而已
    -0.47
    <unused63>
    -0.45
     estekak
    -0.45
     αυτή
    -0.45
     متعلقه
    -0.44
    isen
    -0.41
    POSITIVE LOGITS
    AnchorStyles
    1.00
    RenderAtEndOf
    0.81
    FunctionFlags
    0.77
     typelib
    0.75
    Geplaatst
    0.74
    PhysRevD
    0.72
    Scénario
    0.71
    曖昧さ回避
    0.70
     ModelExpression
    0.70
    AccessorTable
    0.69
    Activations Density 1.266%

    No Known Activations