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. 12-GEMMASCOPE-RES-16K
    6. 15173
    Prev
    Next
    INDEX
    Explanations

    instances of resistance and manipulation in various contexts, such as politics, disease, and competition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hopefully
    -0.52
    ंदीखरीदारी
    -0.50
     fal
    -0.50
     hopefully
    -0.49
     lutter
    -0.46
     mergeFrom
    -0.46
    TagMode
    -0.44
     dient
    -0.43
     aiuta
    -0.43
     Hopefully
    -0.41
    POSITIVE LOGITS
    OrNil
    0.73
    AxisAlignment
    0.68
    InSection
    0.66
    writeFieldEnd
    0.65
     unsc
    0.63
     onOptions
    0.63
    IntoConstraints
    0.61
     counters
    0.61
    ácara
    0.59
     &___
    0.59
    Activations Density 0.623%

    No Known Activations