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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6454
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "comment" and related terms, indicating a focus on commentary and user interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    GenerationType
    -0.62
     BIBSYS
    -0.55
     ſind
    -0.53
     fä
    -0.50
    IntoConstraints
    -0.47
    )))));
    -0.43
    )))))
    -0.42
     sacro
    -0.42
    PageFactory
    -0.42
     uſe
    -0.41
    POSITIVE LOGITS
     Comment
    1.19
     comment
    1.15
    Comment
    1.10
     COMMENT
    1.09
    comment
    1.08
     commenting
    1.02
     comments
    0.99
     Comments
    0.98
    COMMENT
    0.98
     COMMENTS
    0.93
    Activations Density 0.099%

    No Known Activations