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. 23-GEMMASCOPE-RES-16K
    6. 12450
    Prev
    Next
    INDEX
    Explanations

    terms related to educational content and their application in dance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.69
    TagMode
    -0.65
    AndEndTag
    -0.65
     defaultstate
    -0.63
    RenderAtEndOf
    -0.59
     nakalista
    -0.58
     समीक्षक
    -0.57
     Reverso
    -0.56
     للمعارف
    -0.56
    indakan
    -0.55
    POSITIVE LOGITS
     basics
    1.69
     basic
    1.68
     fundamentals
    1.62
    basic
    1.49
     concepts
    1.43
     Basic
    1.38
    Basic
    1.38
     Basics
    1.33
    Basics
    1.33
    basics
    1.33
    Activations Density 0.375%

    No Known Activations