© 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. 10321
    Prev
    Next
    INDEX
    Explanations

    terms related to mistakes or misunderstandings in various contexts

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

    word beginnings and endings

    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
     ostensibly
    -0.59
     admittedly
    -0.52
    FWIW
    -0.51
    ?!?
    -0.49
     interpretive
    -0.48
     gleaned
    -0.45
     decidedly
    -0.44
     bittersweet
    -0.44
    ?!?!
    -0.44
     wacky
    -0.44
    POSITIVE LOGITS
    ChildScrollView
    0.84
     equipments
    0.83
     noOf
    0.73
    MessageOf
    0.71
     ModelExpression
    0.71
    IsContent
    0.70
    +#+#
    0.66
    noOf
    0.65
     learnt
    0.64
     Infórmanos
    0.64
    Activations Density 0.038%

    No Known Activations