© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7828
    Prev
    Next
    INDEX
    Explanations

    references to methods, processes, or uses in a scientific or technical context

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

    followed by an action/function

    np_acts-logits-general · gemini-2.0-flash

    verbs of action or purpose after "to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     using
    -0.96
    using
    -0.87
     Using
    -0.82
    Using
    -0.81
    Use
    -0.80
    use
    -0.80
     Utilizing
    -0.78
     USING
    -0.77
     Use
    -0.76
     utilizzare
    -0.75
    POSITIVE LOGITS
    ]--;
    0.66
     communicate
    0.63
    躇
    0.61
     estekak
    0.60
    choly
    0.60
    ]<<"
    0.58
    χη
    0.57
    hibli
    0.57
    代替
    0.57
     generate
    0.56
    Activations Density 0.518%

    No Known Activations