© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 5362
    Prev
    Next
    INDEX
    Explanations

    terms related to ore processing and specific ore types

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

    oregano, ore, Oreochromis

    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
    ToBounds
    -0.56
    CGContext
    -0.45
    Jakob
    -0.45
     Ví
    -0.44
    verwijspagina
    -0.43
    Gilbert
    -0.43
    Marianne
    -0.43
    IsUnicode
    -0.42
    enschap
    -0.42
     Tama
    -0.42
    POSITIVE LOGITS
     ore
    1.79
     Ore
    1.77
    Ore
    1.60
     ORE
    1.37
     ores
    1.28
     oregano
    0.91
    ore
    0.80
     Oreo
    0.80
     oreo
    0.74
    ORE
    0.73
    Activations Density 0.005%

    No Known Activations