© 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. 20-GEMMASCOPE-RES-131K
    11. 8622
    Prev
    Next
    INDEX
    Explanations

    instances of the conjunction "but," indicating contrasting statements or transitions in arguments

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

    but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ametric
    -0.57
    륭
    -0.56
    󰀄
    -0.54
    ("")]
    -0.54
    ChildScrollView
    -0.53
    ‬‬
    -0.53
     transfieras
    -0.52
     Federated
    -0.52
    __::
    -0.52
    ratory
    -0.52
    POSITIVE LOGITS
    But
    0.72
     But
    0.66
    And
    0.49
     And
    0.49
    Moreover
    0.41
    Pautan
    0.41
    So
    0.41
     Sementara
    0.40
     marcha
    0.39
     médié
    0.38
    Activations Density 0.030%

    No Known Activations