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

    Neuronpedia

    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. 125357
    Prev
    Next
    INDEX
    Explanations

    mentions of wolves and variations of the term "wolf."

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

    wolf, Wolfe, wolfish, wolfram

    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
    CHD
    -0.52
     =&
    -0.51
    />";
    -0.50
    Tikang
    -0.49
    DDI
    -0.47
     CCR
    -0.46
     Gera
    -0.45
    Britney
    -0.45
    Adele
    -0.45
    PreInfinity
    -0.44
    POSITIVE LOGITS
     Wolf
    2.30
    Wolf
    2.23
     WOLF
    1.99
     wolf
    1.98
    wolf
    1.91
     wolves
    1.45
     Wolfs
    1.44
     Wolfe
    1.30
    wolves
    1.30
     Wolves
    1.27
    Activations Density 0.004%

    No Known Activations