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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2086
    Prev
    Next
    INDEX
    Explanations

    terms related to extending or extrapolating information, particularly in theoretical contexts

    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
    脚注の使い方
    -0.48
    GORITH
    -0.46
    QMetaType
    -0.44
    HttpStatus
    -0.41
    bindingNavigator
    -0.41
    MemoryWarning
    -0.40
    GOTREF
    -0.39
    $'
    -0.38
     onPage
    -0.38
    ագրություններ
    -0.38
    POSITIVE LOGITS
     extend
    1.13
     Extend
    1.11
    Extend
    1.05
     extender
    1.02
    extend
    1.02
     Extended
    0.99
    Extended
    0.96
     extended
    0.96
     extension
    0.95
    extended
    0.95
    Activations Density 0.176%

    No Known Activations