© 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. 30-GEMMASCOPE-RES-16K
    11. 10721
    Prev
    Next
    INDEX
    Explanations

    information related to car specifications and performance metrics

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

    speed or quickness

    np_acts-logits-general · gemini-2.0-flash

    fastest acceleration

    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
    getMenuInflater
    -0.46
    transQ
    -0.39
    Anhalt
    -0.38
    Identyfik
    -0.38
    RTLI
    -0.38
     anno
    -0.37
    Tikang
    -0.36
     tele
    -0.35
    hatan
    -0.35
    Gön
    -0.35
    POSITIVE LOGITS
     fastest
    0.80
     Fastest
    0.75
     acceleration
    0.75
     speed
    0.74
    Fastest
    0.73
     velocidad
    0.71
     vitesse
    0.71
    加速
    0.70
     velocidade
    0.69
    速度
    0.68
    Activations Density 0.117%

    No Known Activations