Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2637
    Prev
    Next
    INDEX
    Explanations

    terms related to speed and velocity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    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
    -0.89
    }');
    -0.69
    estero
    -0.69
    ,$_
    -0.68
     institución
    -0.68
    Allo
    -0.67
    anyard
    -0.65
    hlás
    -0.65
    trzy
    -0.64
     instituição
    -0.64
    POSITIVE LOGITS
     Speed
    2.13
     speed
    2.10
    Speed
    2.10
     SPEED
    2.10
    SPEED
    2.07
    speed
    2.03
     speeds
    1.90
    peed
    1.76
     Speeds
    1.69
     vitesse
    1.39
    Activations Density 0.044%

    No Known Activations