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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6902
    Prev
    Next
    INDEX
    Explanations

    numeric values and their associated percentages, particularly in the context of increases and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    IsContent
    -0.50
     дописавши
    -0.43
    WithMany
    -0.43
     trimmer
    -0.42
     pulsera
    -0.42
    CrossRef
    -0.42
     Bioaccumulative
    -0.42
     bescha
    -0.41
     recueil
    -0.41
    ografija
    -0.41
    POSITIVE LOGITS
     समीक्षाएं
    0.44
     disponibilités
    0.41
    jsxFileName
    0.38
     Eocene
    0.35
     interpret
    0.35
    getOutputStream
    0.35
    хівовано
    0.34
     virtually
    0.34
     explo
    0.33
    NewUrlParser
    0.33
    Activations Density 0.884%

    No Known Activations