© 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. 13971
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the potential for blame or excuses in various scenarios

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

    after "to" and other short words

    np_acts-logits-general · gemini-2.0-flash

    personal grooming and hygiene activities

    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
    Referenties
    -0.49
     Komponenten
    -0.48
    KommentareTeilen
    -0.47
     grossen
    -0.47
     pemuda
    -0.44
     allgemeine
    -0.43
     bezig
    -0.42
     sarili
    -0.42
     Anforderungen
    -0.42
     palha
    -0.42
    POSITIVE LOGITS
     shampoo
    0.85
     ketchup
    0.82
     deodorant
    0.79
     hairstyle
    0.76
     toilet
    0.76
     masturb
    0.75
     vegetarian
    0.75
     barbe
    0.74
     hairstyles
    0.73
     pedicure
    0.73
    Activations Density 0.973%

    No Known Activations