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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14920
    Prev
    Next
    INDEX
    Explanations

    elements related to culinary competitions and personal ambitions

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

    Word followed by "in"

    np_acts-logits-general · gemini-2.0-flash

    idiomatic word starters

    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
    AndPassword
    -0.65
    ⓧ
    -0.62
    onViewCreated
    -0.59
    UrlResolution
    -0.59
    raits
    -0.55
     alſo
    -0.54
     osoba
    -0.54
     perſon
    -0.53
     useParams
    -0.51
     referenties
    -0.51
    POSITIVE LOGITS
    ConstraintMaker
    0.68
     pick
    0.67
     McGu
    0.65
     tartalomajánló
    0.61
    LookAnd
    0.61
     grind
    0.59
     blow
    0.57
     swit
    0.57
    lieg
    0.56
     sauve
    0.56
    Activations Density 0.315%

    No Known Activations