© 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. 38-GEMMASCOPE-RES-16K
    11. 7972
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and structure in programming or scripting languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.66
    脚注の使い方
    -0.64
     дописавши
    -0.64
    XmlAccessType
    -0.63
    󠁣
    -0.60
     مشين
    -0.58
     فريبيس
    -0.58
    AndEndTag
    -0.58
    ьаж
    -0.57
    
    -0.57
    POSITIVE LOGITS
    _
    1.61
    _-_
    0.70
    \_
    0.70
    _*
    0.64
    __
    0.57
    ___
    0.51
    _%
    0.50
    _(
    0.50
    _"
    0.50
    _$
    0.49
    Activations Density 2.110%

    No Known Activations