© 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. 696
    Prev
    Next
    INDEX
    Explanations

    references to specific entities and the conditions or requirements surrounding them

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

    contrasting conjunctions like although and while

    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
     հղումներ
    -0.73
    ConstraintMaker
    -0.73
    WithIOException
    -0.71
    
    -0.66
    WireFormatLite
    -0.66
    uxxxx
    -0.65
     pinulongan
    -0.64
    WebServlet
    -0.63
    CodedInputStream
    -0.62
     CURIAM
    -0.60
    POSITIVE LOGITS
     nonetheless
    0.74
     nevertheless
    0.69
     dennoch
    0.59
     still
    0.54
     ainda
    0.51
     aún
    0.49
     néanmoins
    0.48
     vẫn
    0.45
     ändå
    0.45
     tetap
    0.45
    Activations Density 0.102%

    No Known Activations