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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11658
    Prev
    Next
    INDEX
    Explanations

    function calls and parameters in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !
    -0.34
     iné
    -0.32
     antemano
    -0.32
     Administrativna
    -0.32
     continuará
    -0.30
    <bos>
    -0.30
     alike
    -0.30
     ň
    -0.30
    Ӕ
    -0.29
     immense
    -0.29
    POSITIVE LOGITS
    InSection
    0.82
    icksburg
    0.62
     $_(
    0.62
    $_(
    0.58
    addContainerGap
    0.58
     Infórmanos
    0.57
    клопе
    0.56
    ArgsConstructor
    0.55
    abstractmethod
    0.55
     EconPapers
    0.54
    Activations Density 0.141%

    No Known Activations