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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 7685
    Prev
    Next
    INDEX
    Explanations

    references to official entities or organizations, especially related to legal or governmental contexts

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

    "The" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    legal and news subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     passés
    -0.73
     conseguenza
    -0.70
     AssemblyVersion
    -0.69
    anskje
    -0.66
    UserScript
    -0.64
     seguenti
    -0.63
    VersionUID
    -0.62
    providedIn
    -0.62
     vostri
    -0.59
     sahiptir
    -0.59
    POSITIVE LOGITS
     pair
    0.76
     couple
    0.75
     move
    0.74
     incident
    0.74
     statement
    0.70
     governor
    0.68
     duo
    0.65
     woman
    0.65
     plan
    0.65
     unidentified
    0.65
    Activations Density 0.478%

    No Known Activations