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. 13-GEMMASCOPE-RES-16K
    6. 15887
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions related to software licensing

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

    open-source software license headers and legal disclaimer boilerplate in source code files.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.51
     Monfieur
    -0.48
     purpoſe
    -0.46
     ſeveral
    -0.45
     Theſe
    -0.45
     myſelf
    -0.42
    ^(@)
    -0.42
     whoſe
    -0.42
     becauſe
    -0.41
     Majefty
    -0.40
    POSITIVE LOGITS
    <bos>
    1.01
    <eos>
    0.34
    enumi
    0.32
    ρυ
    0.31
    MathML
    0.30
    </tr>
    0.30
     ع
    0.30
    ро
    0.29
    нен
    0.29
    </b>
    0.29
    Activations Density 40.454%

    No Known Activations