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. 19-GEMMASCOPE-RES-16K
    6. 2129
    Prev
    Next
    INDEX
    Explanations

    formatting elements used in text, particularly quotes and block quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.96
     المعيارى
    -0.83
    ollectionView
    -0.82
    Amicalement
    -0.79
    mybatisplus
    -0.78
    EDEFAULT
    -0.78
    endpush
    -0.77
    usermodel
    -0.74
    DOCTYPE
    -0.70
    ⟬
    -0.70
    POSITIVE LOGITS
    <blockquote>
    1.56
    <h4>
    1.13
    <h3>
    1.12
    </blockquote>
    1.09
    <h5>
    1.08
    <h1>
    0.97
    <strong>
    0.95
    <h6>
    0.89
    <em>
    0.88
    <b>
    0.88
    Activations Density 0.015%

    No Known Activations