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. 227
    Prev
    Next
    INDEX
    Explanations

    code snippets that involve function calls and parameter handling in programming languages

    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
     richesse
    -0.33
     змо
    -0.31
     jeunesse
    -0.31
    unduh
    -0.30
    edb
    -0.29
    tdb
    -0.29
     youth
    -0.29
    mancy
    -0.29
     ability
    -0.28
     Rules
    -0.28
    POSITIVE LOGITS
     snippetHide
    0.77
     resourceCulture
    0.65
     intptr
    0.61
    ########.
    0.59
     nakalista
    0.58
     Exacts
    0.58
     surla
    0.57
     informée
    0.57
     تضيفلها
    0.56
    +#+#
    0.55
    Activations Density 1.159%

    No Known Activations