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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 21-GEMMASCOPE-RES-16K
    6. 12542
    Prev
    Next
    INDEX
    Explanations

    descriptions of changes in rates or speeds, particularly in a quantitative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.52
     Infórmanos
    -0.49
    arXiv
    -0.48
    enumi
    -0.47
    ఞ
    -0.46
    ushan
    -0.46
     الاطلاع
    -0.46
    contentLoaded
    -0.45
    rician
    -0.44
     defStyle
    -0.44
    POSITIVE LOGITS
     speed
    2.70
     faster
    2.39
     speeds
    2.33
    speed
    2.33
     fast
    2.30
     Speed
    2.20
    Speed
    2.15
     SPEED
    2.13
     fastest
    2.10
    faster
    2.07
    Activations Density 0.710%

    No Known Activations