© 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. 9-GEMMASCOPE-RES-16K
    11. 5981
    Prev
    Next
    INDEX
    Explanations

    code elements related to method definitions and declarations in programming

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

    Code related to NSCoder's encodeWithCoder/initWithCoder methods

    np_acts-logits-general · gemini-2.0-flash

    objective-c and swift code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orithmic
    -0.50
    complexContent
    -0.49
    TargetException
    -0.47
    multicolumn
    -0.47
     שוליים
    -0.46
    ChildScrollView
    -0.45
    ⮕
    -0.43
    RenderAtEndOf
    -0.42
    Xna
    -0.42
    styleUrls
    -0.42
    POSITIVE LOGITS
     UIKit
    0.65
     _$
    0.48
    Sklici
    0.48
     Biôgrafia
    0.47
     tropicales
    0.45
    sidemargin
    0.44
    хьтан
    0.44
    IVEREF
    0.43
     costes
    0.43
    ExceptionHandler
    0.42
    Activations Density 0.027%

    No Known Activations