© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9034
    Prev
    Next
    INDEX
    Explanations

    HTML heading and list elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML tags (h1, p, li, h4)

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    AddTagHelper
    -0.61
     MainAxisSize
    -0.55
     Abp
    -0.54
     protoimpl
    -0.50
    Portail
    -0.48
    новниш
    -0.46
     JpaRepository
    -0.46
    
    -0.45
     FetchType
    -0.45
    +#+
    -0.43
    POSITIVE LOGITS
    LabelTagHelper
    0.54
    BibitemShut
    0.45
     Lübeck
    0.45
     carottes
    0.44
    ViewFeatures
    0.44
     defaultstate
    0.43
    <h3>
    0.43
    ɵɵelementStart
    0.42
    intérêt
    0.41
    subsection
    0.40
    Activations Density 0.029%

    No Known Activations