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. 6792
    Prev
    Next
    INDEX
    Explanations

    segments of code and markup related to structured programming and templating syntax

    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
    SharedCtor
    -0.68
     AssemblyTitle
    -0.66
     simplifié
    -0.60
     BEGINNING
    -0.58
     beginning
    -0.56
    Rhestr
    -0.56
    ゴリー
    -0.54
    WebServlet
    -0.54
     ISNI
    -0.53
     inicio
    -0.53
    POSITIVE LOGITS
     closing
    0.97
     End
    0.95
    End
    0.94
     END
    0.91
     end
    0.91
     ends
    0.89
    glEnd
    0.86
     "</
    0.85
     ending
    0.85
    ("</
    0.82
    Activations Density 0.502%

    No Known Activations