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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 7540
    Prev
    Next
    INDEX
    Explanations

    HTML tags, particularly bold and strong formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    öscht
    -0.67
    ''');
    -0.67
    ↵↵
    -0.66
    ificance
    -0.63
    abá
    -0.63
    öp
    -0.62
    Quy
    -0.60
    Glej
    -0.60
    neux
    -0.60
    ‬‬
    -0.59
    POSITIVE LOGITS
    <strong>
    1.90
    <em>
    1.62
    <b>
    1.38
    <u>
    1.31
    <code>
    1.15
    </strong>
    1.14
    <i>
    1.11
    <s>
    0.97
    <sub>
    0.95
    “
    0.86
    Activations Density 0.005%

    No Known Activations