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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 5173
    Prev
    Next
    INDEX
    Explanations

    programming constructs and definitions within code

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

    c preprocessor defines

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    onOptions
    -0.51
     CreateTagHelper
    -0.48
    exitRule
    -0.47
    EndContext
    -0.43
    adaptiveStyles
    -0.42
    Vidite
    -0.42
     }{@
    -0.41
    }{*}{}
    -0.39
     useAppContext
    -0.39
     quedado
    -0.39
    POSITIVE LOGITS
    define
    2.73
     define
    1.65
    Define
    1.50
     Define
    1.48
    defines
    1.24
     defines
    1.19
     defining
    1.13
     Defining
    1.09
    defining
    1.09
    DEFINE
    1.07
    Activations Density 0.015%

    No Known Activations