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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8132
    Prev
    Next
    INDEX
    Explanations

    elements related to identity, qualifications, and potentially misleading statements in a descriptive context

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

    Text related to personal identification, particularly phrases where someone states or claims their identity, position, affiliation, or background in formal contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ostom
    -0.36
    COM
    -0.36
    حياته
    -0.35
    EnableWeb
    -0.35
    Application
    -0.34
    Eu
    -0.34
    oredCriteria
    -0.34
    oria
    -0.34
    bereit
    -0.34
     Application
    -0.34
    POSITIVE LOGITS
     AssemblyCompany
    0.69
    rungsseite
    0.60
     credentials
    0.60
    StoryboardSegue
    0.58
    IntoConstraints
    0.56
     qualifications
    0.53
    InjectAttribute
    0.52
     Credentials
    0.51
    Werdegang
    0.50
     profesión
    0.50
    Activations Density 0.081%

    No Known Activations