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. 12-GEMMASCOPE-RES-16K
    6. 7490
    Prev
    Next
    INDEX
    Explanations

    references to crews and groups in various contexts

    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
    ρίου
    -0.80
    oporosis
    -0.78
     Theron
    -0.73
    googleapis
    -0.73
    oldValue
    -0.72
     Chwiliwch
    -0.71
    coats
    -0.71
    ukone
    -0.69
     François
    -0.68
    aarrggbb
    -0.68
    POSITIVE LOGITS
     Cabral
    0.79
    oughby
    0.79
    SourceChecksum
    0.76
     Kami
    0.75
    USART
    0.73
     Soul
    0.71
    soul
    0.71
    Chore
    0.70
    Soul
    0.70
     crews
    0.70
    Activations Density 0.312%

    No Known Activations