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. 4-GEMMASCOPE-RES-16K
    6. 3180
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and organizations, particularly related to cybersecurity and notable incidents in Ozark, Alabama

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pagos
    -0.70
     buddha
    -0.70
     Vex
    -0.69
     Neve
    -0.68
     Firestone
    -0.68
    mAuth
    -0.67
     heather
    -0.67
    Thumbs
    -0.67
    EndInit
    -0.66
     Ub
    -0.65
    POSITIVE LOGITS
     صوتيه
    0.68
    djangoproject
    0.61
     Pry
    0.58
    readAs
    0.58
    pertory
    0.56
     Nucle
    0.56
    isNameExpr
    0.55
     Mustafa
    0.55
     nucle
    0.55
    semibold
    0.53
    Activations Density 5.877%

    No Known Activations