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

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 14649
    Prev
    Next
    INDEX
    Explanations

    names and titles of artistic works or productions

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

    references to rap artists and hip-hop music.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gink
    -0.35
     plomb
    -0.34
    })();
    -0.34
     Scheiben
    -0.33
     recue
    -0.33
     huel
    -0.32
     hong
    -0.32
     typelib
    -0.31
    Datuak
    -0.30
    Phaser
    -0.30
    POSITIVE LOGITS
     rappers
    0.79
     rapper
    0.69
     raps
    0.69
     mixtape
    0.64
     niggas
    0.60
     rap
    0.59
    rapper
    0.58
     visuals
    0.57
     rapping
    0.56
     Trap
    0.55
    Activations Density 0.120%

    No Known Activations