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. 11-GEMMASCOPE-RES-16K
    6. 6927
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to manual, handcrafted, or hand-operated items and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McClure
    -0.87
     odkazy
    -0.86
    -------
    -0.86
    redients
    -0.83
    Poem
    -0.82
    ized
    -0.82
     Trotz
    -0.80
    ergies
    -0.77
     poems
    -0.77
    Portale
    -0.75
    POSITIVE LOGITS
     Hands
    1.62
     HAND
    1.60
    HAND
    1.59
     Hand
    1.58
    Hand
    1.57
     hands
    1.55
     hand
    1.52
    hand
    1.48
    Hands
    1.47
     HANDS
    1.35
    Activations Density 0.064%

    No Known Activations