© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 12997
    Prev
    Next
    INDEX
    Explanations

    phrases signaling a call to action or a request to begin something

    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
     ModelExpression
    -0.68
     saites
    -0.68
     disponibilités
    -0.65
     resourceCulture
    -0.64
    Autoritní
    -0.64
    sidemargin
    -0.61
     umane
    -0.59
     Wiktionnaire
    -0.57
    aarrggbb
    -0.54
    PyExc
    -0.54
    POSITIVE LOGITS
     break
    0.75
    そろそろ
    0.73
    break
    0.70
     time
    0.65
     momento
    0.62
     TIME
    0.60
     big
    0.60
     artık
    0.59
    time
    0.58
     BREAK
    0.57
    Activations Density 0.127%

    No Known Activations