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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 116877
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "names" and related phrases

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

    referring to names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dieses
    -0.43
     prêtres
    -0.42
     verksamhet
    -0.41
     Wettbewerb
    -0.41
     asta
    -0.40
     cortex
    -0.40
     Dieser
    -0.40
     Erkrankung
    -0.40
     aportar
    -0.40
     curvas
    -0.40
    POSITIVE LOGITS
     names
    1.98
     Names
    1.70
    names
    1.59
     NAMES
    1.42
    Names
    1.41
    NAMES
    1.22
     nombres
    1.11
     nomes
    1.11
    enames
    1.08
     имена
    0.92
    Activations Density 0.012%

    No Known Activations