© 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. 9283
    Prev
    Next
    INDEX
    Explanations

    identifiers and their relationships within code or data structures

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

    Immediately precedes "the" or "to"

    np_acts-logits-general · gemini-2.0-flash

    paths or URLs

    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
    ViewFeatures
    -0.64
     saites
    -0.60
    Дереккөздер
    -0.60
    tagHelperRunner
    -0.59
    aronder
    -0.59
    HtmlAttribute
    -0.58
    enderror
    -0.56
    urtz
    -0.56
    ValueStyle
    -0.55
    ollectionView
    -0.55
    POSITIVE LOGITS
     متعلقه
    0.73
    上一
    0.57
    下一个
    0.51
     corresponding
    0.51
    ISupport
    0.50
     ModelExpression
    0.49
     class
    0.49
     typelib
    0.49
    malink
    0.49
    MENAFN
    0.49
    Activations Density 0.340%

    No Known Activations