Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12476
    Prev
    Next
    INDEX
    Explanations

    verbs associated with processes and actions taken in various contexts

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

    Comes after a past-participle verb

    np_acts-logits-general · gemini-2.0-flash

    actions completed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kusen
    -0.37
    ToBounds
    -0.37
    conexion
    -0.36
    /
    -0.35
    Besos
    -0.35
     previsão
    -0.35
     приш
    -0.35
    nologue
    -0.35
    URLException
    -0.34
    ländische
    -0.33
    POSITIVE LOGITS
     iprot
    0.54
     nakalista
    0.52
    ftagPool
    0.52
     kasarigan
    0.50
    DockStyle
    0.49
    Diweddarwch
    0.48
     transfieras
    0.48
    providedIn
    0.48
     regarding
    0.48
    regarding
    0.48
    Activations Density 0.590%

    No Known Activations