© 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. 38465
    Prev
    Next
    INDEX
    Explanations

    various emotional states and actions related to surprise or strong reactions

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

    words starting with 'a' indicating state or position

    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
     judiciales
    -0.56
    cupertino
    -0.56
     avoient
    -0.56
     miniaturka
    -0.56
     feroit
    -0.56
     exécut
    -0.54
     plufieurs
    -0.54
     fédé
    -0.54
     vectorielle
    -0.53
    resizingMask
    -0.51
    POSITIVE LOGITS
     afloat
    0.71
     adrift
    0.69
     aloft
    0.68
     alight
    0.68
     afield
    0.60
     afar
    0.59
     ablaze
    0.56
     amiss
    0.56
     abreast
    0.54
     Alo
    0.53
    Activations Density 0.018%

    No Known Activations