© 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. 8-GEMMASCOPE-RES-16K
    11. 6074
    Prev
    Next
    INDEX
    Explanations

    terms associated with successful media, particularly focusing on "hits" and "bestsellers."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    陋
    -0.38
    okai
    -0.38
     Poetry
    -0.38
     geb
    -0.37
     szak
    -0.36
    bau
    -0.35
    Poetry
    -0.35
    ður
    -0.35
     Poet
    -0.35
     Silber
    -0.35
    POSITIVE LOGITS
     hit
    1.11
     hits
    1.01
    ヒット
    0.89
     Hit
    0.84
    hits
    0.84
    hit
    0.82
     Hits
    0.81
    Hit
    0.79
     popular
    0.78
    HIT
    0.77
    Activations Density 0.216%

    No Known Activations