Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1608
    Prev
    Next
    INDEX
    Explanations

    titles and designations of individuals in an organizational or governmental context

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

    Titles such as assistant, deputy, vice

    np_acts-logits-general · gemini-2.0-flash

    deputy, vice, assistant roles

    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
     дописавши
    -0.68
     يتيمه
    -0.63
     keines
    -0.54
     isComment
    -0.52
     läng
    -0.51
     chinoise
    -0.50
    sing
    -0.50
    ổ
    -0.49
    ifiers
    -0.48
     Brasileiro
    -0.47
    POSITIVE LOGITS
    bootstrapcdn
    0.73
    ActionCreators
    0.70
    ///</
    0.70
    SourceChecksum
    0.68
    PUTY
    0.67
    ViewImports
    0.67
    haustible
    0.67
    enumii
    0.67
    awakeFromNib
    0.66
    WebpackPlugin
    0.65
    Activations Density 0.089%

    No Known Activations