© 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 EvalsExportsAPI 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. 13376
    Prev
    Next
    INDEX
    Explanations

    dialogue that conveys questions and responses, especially centered around personal relationships and social interactions

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

    Follows quotation marks

    np_acts-logits-general · gemini-2.0-flash

    phrase starters after punctuation

    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
     freakin
    -0.85
     guys
    -0.82
     dude
    -0.80
     dudes
    -0.79
     freaking
    -0.76
     freaked
    -0.75
     Roskov
    -0.75
     GUYS
    -0.74
    guys
    -0.73
     wanna
    -0.71
    POSITIVE LOGITS
    Quite
    0.46
     quite
    0.45
     senhor
    0.44
     Quite
    0.44
     gentlemen
    0.43
    quite
    0.42
     tačiau
    0.42
     fará
    0.41
     mężczy
    0.41
     velmi
    0.40
    Activations Density 0.272%

    No Known Activations