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. 21-GEMMASCOPE-RES-16K
    6. 1048
    Prev
    Next
    INDEX
    Explanations

    HTML or XML closing tags and comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.33
     Efq
    -1.25
     itſelf
    -1.19
     myſelf
    -1.18
     Houſe
    -1.17
     ſeveral
    -1.15
     leaſt
    -1.12
     whoſe
    -1.11
     houſe
    -1.11
     uſed
    -1.10
    POSITIVE LOGITS
    <em>
    1.04
    </em>
    0.86
    <i>
    0.82
    <u>
    0.68
    <sup>
    0.63
    <eos>
    0.63
    <sub>
    0.63
    </i>
    0.63
    ↵↵
    0.63
    ↵
    0.58
    Activations Density 0.157%

    No Known Activations