© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6447
    Prev
    Next
    INDEX
    Explanations

    the word "come" in various forms and contexts

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

    come Saturday morning

    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
     gynhyrchwyd
    -0.49
     StyleSheet
    -0.49
    athyroid
    -0.48
     douceur
    -0.47
     Szk
    -0.47
     utilizing
    -0.47
     giornal
    -0.47
    forests
    -0.46
    Ehrungen
    -0.46
    deviceId
    -0.45
    POSITIVE LOGITS
     come
    1.86
    come
    1.81
    Come
    1.73
     Come
    1.67
     COME
    1.54
    COME
    1.45
     comes
    1.28
    comes
    1.23
     came
    1.17
    came
    1.14
    Activations Density 0.016%

    No Known Activations