© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 149
    Prev
    Next
    INDEX
    Explanations

    technical terms and comments related to programming constructs and operations

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

    German words ending in aß or uß

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     functionalities
    -0.77
    OGND
    -0.76
    ⌝
    -0.71
     ―――――
    -0.66
    〮
    -0.65
     softwares
    -0.65
    casted
    -0.64
     ️
    -0.63
     onboarding
    -0.63
    testify
    -0.61
    POSITIVE LOGITS
     daß
    0.71
     muß
    0.69
    faßt
    0.57
     läßt
    0.54
     Miß
    0.53
     biß
    0.52
     Daß
    0.50
     Schluß
    0.50
     müßte
    0.45
    wußt
    0.43
    Activations Density 0.091%

    No Known Activations