© 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. 31-GEMMASCOPE-RES-131K
    11. 10162
    Prev
    Next
    INDEX
    Explanations

    references to iron and its various forms or related contexts

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

    iron

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementGuid
    -0.43
     despacho
    -0.38
    PreInfinity
    -0.37
     eens
    -0.33
    sweise
    -0.33
    innocent
    -0.33
    комму
    -0.32
    peth
    -0.32
    ulipas
    -0.32
    contentLoaded
    -0.31
    POSITIVE LOGITS
     Iron
    0.75
    Iron
    0.75
     Irons
    0.73
     iron
    0.69
     IRON
    0.65
    IRON
    0.64
     Eisen
    0.62
    iron
    0.61
     Ferro
    0.60
     irons
    0.60
    Activations Density 0.022%

    No Known Activations