© 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. 465
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and institutions

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

    cities and universities

    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
     avoient
    -0.40
     auroit
    -0.38
     étoient
    -0.33
     étoit
    -0.32
     dejes
    -0.30
     quedado
    -0.30
     pouvoit
    -0.29
    webElement
    -0.29
     mourut
    -0.27
     feroit
    -0.27
    POSITIVE LOGITS
    脚注の使い方
    0.71
     deſſen
    0.69
    𑄮
    0.63
     ſehr
    0.62
    𑄝
    0.62
     unſer
    0.61
     beſte
    0.61
     ſeiner
    0.61
    ſammen
    0.60
    principalColumn
    0.60
    Activations Density 0.046%

    No Known Activations