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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 675
    Prev
    Next
    INDEX
    Explanations

    references to education and safety-related issues

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

    news and reporting captions

    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
     actualidad
    -0.37
     grateful
    -0.34
    bo
    -0.33
     Einzel
    -0.32
    prze
    -0.32
     variar
    -0.32
    itemView
    -0.31
     Hinblick
    -0.30
     wisely
    -0.30
     gradually
    -0.30
    POSITIVE LOGITS
     tartalomajánló
    0.71
    SharedDtor
    0.69
     allegedly
    0.63
     EconPapers
    0.62
    ſelf
    0.61
     ब्रेकडाउन
    0.61
    zzleHttp
    0.60
     الحره
    0.60
    alleg
    0.59
     alleged
    0.59
    Activations Density 0.058%

    No Known Activations