Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8330
    Prev
    Next
    INDEX
    Explanations

    references to the pronoun "this" in various contexts

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

    this. member access

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Wikiseite
    -0.49
    transQ
    -0.45
     crossorigin
    -0.40
     дописавши
    -0.40
     onCancelled
    -0.40
    haja
    -0.40
     alguno
    -0.38
    createStatement
    -0.38
     alguna
    -0.37
     Verhältnisse
    -0.36
    POSITIVE LOGITS
    Diweddarwch
    0.72
     AssemblyCulture
    0.59
     ControllerBase
    0.49
     ContentValues
    0.48
     StatelessWidget
    0.46
     MonoBehaviour
    0.45
     NgModule
    0.44
    ArrowToggle
    0.43
    رشف
    0.42
     समीक्षक
    0.41
    Activations Density 0.003%

    No Known Activations