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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 51487
    Prev
    Next
    INDEX
    Explanations

    the word "actually" in various contexts

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

    actually followed by verb

    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
     initComponents
    -0.53
     Codable
    -0.50
    interopRequire
    -0.49
     Cortez
    -0.47
     Bernadette
    -0.46
    шенный
    -0.46
     Pender
    -0.45
     sœur
    -0.45
     GSC
    -0.45
     affid
    -0.44
    POSITIVE LOGITS
     actually
    1.07
    actually
    1.05
    Actually
    0.85
     ACTUALLY
    0.84
     Actually
    0.83
     actual
    0.72
    actual
    0.70
    Actual
    0.68
     реально
    0.65
     Actual
    0.65
    Activations Density 0.013%

    No Known Activations