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. 22-GEMMASCOPE-RES-16K
    6. 10401
    Prev
    Next
    INDEX
    Explanations

    references to significant events and milestones in personal lives, particularly weddings and anniversaries

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

    Follows "Governor" or relates to transitions

    np_acts-logits-general · gemini-2.0-flash

    Governor announcing public health measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endsection
    -0.53
     contextLoads
    -0.48
    arXiv
    -0.47
    ường
    -0.46
    WithIdentifier
    -0.46
    </thead>
    -0.46
    LTE
    -0.45
    商品説明
    -0.44
     AnyObject
    -0.43
    buch
    -0.43
    POSITIVE LOGITS
     vaccine
    0.71
     quarantine
    0.71
     Quarantine
    0.69
     MenuView
    0.69
    ArrowToggle
    0.67
    IBOutlet
    0.65
    MenuView
    0.65
     Virus
    0.65
    Virus
    0.63
    vaccine
    0.63
    Activations Density 0.090%

    No Known Activations