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. 4-GEMMASCOPE-RES-16K
    6. 11179
    Prev
    Next
    INDEX
    Explanations

    markup or formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brito
    -0.78
    OGND
    -0.76
     Drayton
    -0.72
    expandindo
    -0.70
    Portály
    -0.67
    arakhand
    -0.67
    writerow
    -0.66
     Charleston
    -0.65
    codecs
    -0.65
    )//
    -0.65
    POSITIVE LOGITS
    </em>
    0.92
    __(/*!
    0.87
    脚注の使い方
    0.85
    hyr
    0.78
    </i>
    0.76
    <h6>
    0.76
     Pac
    0.71
    BagConstraints
    0.68
     cunt
    0.68
     Nae
    0.67
    Activations Density 0.177%

    No Known Activations