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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1391
    Prev
    Next
    INDEX
    Explanations

    mentions of food-related topics and consumption patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "food" followed by descriptive words

    np_acts-logits-general · gemini-2.0-flash

    food, drug, water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]";
    -1.01
    )"),
    -0.99
    )");
    
    -0.95
    ."]
    -0.92
    BibitemShut
    -0.92
    \"");
    -0.92
    ']],
    -0.91
    ."),
    -0.91
    ])]
    -0.90
    ."</
    -0.90
    POSITIVE LOGITS
    -
    0.66
    y
    0.63
    z
    0.63
    w
    0.63
    H
    0.62
    f
    0.62
    b
    0.61
    P
    0.60
    man
    0.59
    k
    0.59
    Activations Density 0.577%

    No Known Activations