© 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. 18-GEMMASCOPE-RES-16K
    11. 1608
    Prev
    Next
    INDEX
    Explanations

    references to legal entities and court proceedings

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

    Legal roles/titles followed by a possessive apostrophe

    np_acts-logits-general · gemini-2.0-flash

    legal roles followed by apostrophes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    다는
    -0.52
    BARA
    -0.51
    ็จ
    -0.48
    cinoma
    -0.47
    urek
    -0.46
    msch
    -0.46
     Blas
    -0.46
    ULES
    -0.46
    undai
    -0.45
    zzá
    -0.45
    POSITIVE LOGITS
    ’
    1.31
    '
    1.28
    $'
    1.08
    <bos>
    1.08
    ]'
    0.73
    ‟
    0.72
    ´
    0.67
    ’
    0.67
    }'
    0.67
    ův
    0.66
    Activations Density 0.942%

    No Known Activations