© 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. 550
    Prev
    Next
    INDEX
    Explanations

    names of individuals in a legal context

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

    first and last names

    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
    Erstellt
    -0.42
    //</
    -0.39
     didst
    -0.37
     Transparent
    -0.35
     inse
    -0.34
     transparent
    -0.33
     Spinning
    -0.33
    ransition
    -0.32
    NESOTA
    -0.32
    ISupport
    -0.32
    POSITIVE LOGITS
    pecabe
    0.68
    brinco
    0.58
     otomatig
    0.57
     telefónica
    0.55
     فريبيس
    0.54
     Paglinawan
    0.51
     unknownFields
    0.51
    sapato
    0.50
     endregion
    0.49
    meester
    0.48
    Activations Density 0.016%

    No Known Activations