© 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. 329
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses introducing subordinate clauses or additional information about a subject

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

    elaboration using which

    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
     unlike
    -0.48
     Unlike
    -0.47
    Unlike
    -0.41
     ModelExpression
    -0.39
    unlike
    -0.38
    >*/
    -0.35
     compared
    -0.33
     fes
    -0.33
     Ul
    -0.33
     Compared
    -0.32
    POSITIVE LOGITS
     miniaturka
    0.69
     Geſch
    0.63
     فريبيس
    0.62
    AndEndTag
    0.61
    ตาย
    0.58
     Infór
    0.57
     wcześ
    0.57
    uales
    0.57
     Wikiseite
    0.57
     Geiſt
    0.56
    Activations Density 0.071%

    No Known Activations