© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 98755
    Prev
    Next
    INDEX
    Explanations

    mentions of coils and related electromagnetic components

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

    coil, coiled, coiling, recoil

    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
    adaptiveStyles
    -0.52
     Tade
    -0.50
     '':
    -0.50
    estacks
    -0.48
     intptr
    -0.48
     Lus
    -0.48
    ❚
    -0.47
     Democ
    -0.46
     Fram
    -0.45
     Eben
    -0.45
    POSITIVE LOGITS
     coil
    2.44
     Coil
    2.20
    Coil
    2.17
    coil
    2.02
     coils
    1.96
     bobina
    1.41
     coiled
    1.37
    Helix
    0.77
    helix
    0.76
     helix
    0.75
    Activations Density 0.004%

    No Known Activations