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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14131
    Prev
    Next
    INDEX
    Explanations

    statements or phrases indicating suggestions or recommendations

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

    followed by "that" related to suggestion

    np_acts-logits-general · gemini-2.0-flash

    indicates a suggestion or inference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    multer
    -0.35
     Rau
    -0.34
     gra
    -0.34
     Astron
    -0.33
     Bâ
    -0.33
    Иск
    -0.31
     Krieger
    -0.31
     bonded
    -0.30
    Astr
    -0.30
     Walton
    -0.29
    POSITIVE LOGITS
     Suggestion
    0.86
     suggestion
    0.83
    Suggest
    0.82
    suggestion
    0.82
     Suggest
    0.82
    Suggested
    0.81
     Suggested
    0.80
    Suggestion
    0.79
    suggest
    0.79
     suggest
    0.75
    Activations Density 0.175%

    No Known Activations