Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 119584
    Prev
    Next
    INDEX
    Explanations

    references to indigenous cultures and handcrafted items

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

    handicrafts and art

    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
     cabriolet
    -0.40
     Armada
    -0.40
     probl
    -0.38
    BASEPATH
    -0.37
     problems
    -0.36
     paran
    -0.36
     sade
    -0.36
     Staffing
    -0.35
     Probl
    -0.35
     vital
    -0.35
    POSITIVE LOGITS
     handicrafts
    0.56
     lenker
    0.56
    GOTREF
    0.54
     Pottery
    0.53
     pottery
    0.52
     art
    0.51
    gsSP
    0.50
     Kunst
    0.49
     kunst
    0.49
    Kunst
    0.48
    Activations Density 0.065%

    No Known Activations