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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2523
    Prev
    Next
    INDEX
    Explanations

    markup or formatting elements, particularly italics and bold tags

    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
    må
    -0.70
     Drummond
    -0.69
     Wiel
    -0.66
    GenerationType
    -0.66
    //
    -0.65
    rinfo
    -0.65
    dı
    -0.64
     Braxton
    -0.63
     fortal
    -0.62
    ticultural
    -0.62
    POSITIVE LOGITS
    </em>
    1.25
    /*
    1.22
    <em>
    1.18
    <i>
    1.17
    </i>
    1.03
    __(/*!
    0.99
    possum
    0.94
     Spill
    0.94
     Nils
    0.93
    icordia
    0.93
    Activations Density 0.030%

    No Known Activations