© 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. 476
    Prev
    Next
    INDEX
    Explanations

    code structure elements primarily related to defining and closing blocks or functions

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

    response amplitudes

    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
     kasarigan
    -0.87
    AddTagHelper
    -0.73
     StatefulWidget
    -0.68
     مرئيه
    -0.63
    SharedDtor
    -0.63
    GEBURTSDATUM
    -0.62
    Hentet
    -0.61
    OGND
    -0.61
    tvguidetime
    -0.61
    FormTagHelper
    -0.59
    POSITIVE LOGITS
    Third
    0.45
     mínimos
    0.43
    Continuar
    0.42
     Púb
    0.41
     Utama
    0.40
    warnai
    0.37
    Nature
    0.36
     cláus
    0.36
     bø
    0.35
     povin
    0.35
    Activations Density 0.022%

    No Known Activations