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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 3231
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or constructs in structured code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.58
    invokeLater
    -0.56
    ValueStyle
    -0.47
     betweenstory
    -0.45
    oredCriteria
    -0.44
    ArrowToggle
    -0.42
     ligiloj
    -0.42
    éndolo
    -0.42
    MENAFN
    -0.41
     disambiguazione
    -0.40
    POSITIVE LOGITS
     base
    4.09
     Base
    3.59
    base
    3.55
    Base
    3.27
     BASE
    3.16
     bases
    2.97
    BASE
    2.91
     Bases
    2.63
    bases
    2.58
     getBase
    2.58
    Activations Density 1.719%

    No Known Activations