© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10306
    Prev
    Next
    INDEX
    Explanations

    elements related to coding structures and functions, particularly in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.50
     yyr
    -0.47
     defStyleAttr
    -0.43
     ODS
    -0.40
    참고
    -0.38
    endforeach
    -0.37
    ː
    -0.37
    ⁂
    -0.36
    ODS
    -0.36
    //-->
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    0.67
     wireType
    0.62
     disambiguazione
    0.57
     autorytatywna
    0.56
    GOTREF
    0.54
    $_['
    0.50
    setVerticalGroup
    0.49
    ScopeManager
    0.48
    setPointSize
    0.47
     feroit
    0.45
    Activations Density 1.127%

    No Known Activations