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. 25-GEMMASCOPE-RES-16K
    6. 3812
    Prev
    Next
    INDEX
    Explanations

    closure and structural elements in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.95
    GEBURTSDATUM
    -0.93
    ValueStyle
    -0.87
    richTextPanel
    -0.78
     AssemblyCulture
    -0.72
    <eos>
    -0.72
     unknownFields
    -0.72
    Manbalar
    -0.70
    webElementXpaths
    -0.69
    principalTable
    -0.68
    POSITIVE LOGITS
    </b>
    1.03
    </strong>
    0.91
    </i>
    0.86
    </h2>
    0.78
    </em>
    0.76
    </u>
    0.67
    "};
    0.58
    </code>
    0.57
    '};
    0.54
     */;
    0.53
    Activations Density 0.157%

    No Known Activations