Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 5025
    Prev
    Next
    INDEX
    Explanations

    timestamps and dates in the text

    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
     Efq
    -1.15
     Monfieur
    -1.00
    ]--;
    -0.88
    ſelves
    -0.86
     ſeveral
    -0.84
     Eſ
    -0.84
     Majefty
    -0.83
     auffi
    -0.81
    >`;
    -0.79
     greateſt
    -0.79
    POSITIVE LOGITS
    <eos>
    0.60
    I
    0.54
    ↵
    0.53
    ↵↵
    0.46
     akkor
    0.43
    GEBURTSDATUM
    0.43
    D
    0.42
    U
    0.42
     кро
    0.42
    .
    0.42
    Activations Density 0.107%

    No Known Activations