© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7656
    Prev
    Next
    INDEX
    Explanations

    punctuation and conversational markers in text

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

    Follows a quotation mark and a space

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h5>
    -0.55
     esternos
    -0.48
    </caption>
    -0.46
     ModelExpression
    -0.43
    ↵↵
    -0.41
     ſur
    -0.40
     sors
    -0.38
     («
    -0.36
    %;
    -0.36
    的产品
    -0.36
    POSITIVE LOGITS
    .”
    0.97
    ."
    0.88
    ”.
    0.84
    。”
    0.82
    ".
    0.78
    ?”
    0.75
    !”
    0.73
    !"
    0.71
    ").
    0.69
    )."
    0.69
    Activations Density 0.281%

    No Known Activations