© 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. 11898
    Prev
    Next
    INDEX
    Explanations

    lyrics and references to music and artists

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

    rap music and rappers

    np_acts-logits-general · gemini-2.0-flash

    rap culture and artists

    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
     jadx
    -0.35
    gink
    -0.33
     huel
    -0.32
     😃
    -0.31
    matchCondition
    -0.31
    Smarty
    -0.31
    (=)
    -0.31
     vuestra
    -0.31
    })();
    -0.30
     hong
    -0.29
    POSITIVE LOGITS
     rappers
    0.81
     rapper
    0.73
     rap
    0.68
     mixtape
    0.67
     niggas
    0.67
     raps
    0.66
     rapping
    0.62
    rapper
    0.59
     Rap
    0.58
     nigga
    0.58
    Activations Density 0.156%

    No Known Activations