© 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. 16-GEMMASCOPE-RES-16K
    11. 5430
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and asterisks

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

    Tokens surrounded by asterisks

    np_acts-logits-general · gemini-2.0-flash

    numerical lists or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vrolet
    -0.91
    otheby
    -0.83
    ousands
    -0.82
    NUMX
    -0.82
    uawei
    -0.82
    vielen
    -0.79
    stdc
    -0.79
    cửa
    -0.77
    ratulations
    -0.77
    ^(@)
    -0.77
    POSITIVE LOGITS
     
    0.73
    ↵↵
    0.72
     *
    0.61
    *
    0.60
     The
    0.57
     When
    0.56
    ·
    0.53
    li
    0.53
    by
    0.52
    <eos>
    0.52
    Activations Density 0.423%

    No Known Activations