© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 240
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement of speed and acceleration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anfitrión
    -0.85
    [@"
    -0.69
     hilt
    -0.69
    estero
    -0.69
    }');
    -0.66
     Cabot
    -0.64
    hringer
    -0.64
     Stedman
    -0.63
    OTA
    -0.63
     Rami
    -0.63
    POSITIVE LOGITS
     speed
    2.63
     Speed
    2.57
    Speed
    2.55
    speed
    2.53
     SPEED
    2.47
    SPEED
    2.43
     speeds
    2.35
    peed
    2.08
     Speeds
    2.08
     vitesse
    1.74
    Activations Density 0.056%

    No Known Activations