© 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. 1835
    Prev
    Next
    INDEX
    Explanations

    terms associated with mathematical or logical data structures and hierarchy

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

    Followed by "term", "act", "root", or "row"

    np_acts-logits-general · gemini-2.0-flash

    required, specific, single items

    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
    providedIn
    -0.48
    umber
    -0.43
    esModule
    -0.42
    ols
    -0.41
    Invoker
    -0.40
    icker
    -0.39
    mens
    -0.39
    GREES
    -0.39
    mids
    -0.38
    Arrays
    -0.38
    POSITIVE LOGITS
     виправивши
    0.82
    antMatchers
    0.80
    bootstrapcdn
    0.77
     للمعارف
    0.75
    TagMode
    0.72
    istoitu
    0.71
     récentes
    0.69
     للاسماء
    0.69
     fédé
    0.67
     tslint
    0.67
    Activations Density 0.712%

    No Known Activations