© 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10848
    Prev
    Next
    INDEX
    Explanations

    instances of the word "come" in various contexts

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

    "Come" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    come patterns

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Szk
    -0.54
     gynhyrchwyd
    -0.52
     ſmall
    -0.52
    ByUserId
    -0.50
    tayl
    -0.50
    printStats
    -0.50
     Statisti
    -0.49
    ercito
    -0.49
     ſche
    -0.48
     ſch
    -0.48
    POSITIVE LOGITS
     come
    1.59
    Come
    1.35
    come
    1.34
     Come
    1.34
     COME
    1.33
     comes
    1.31
     came
    1.30
     coming
    1.20
     Comes
    1.20
    Comes
    1.19
    Activations Density 0.093%

    No Known Activations