© 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. 9-GEMMASCOPE-RES-131K
    11. 50273
    Prev
    Next
    INDEX
    Explanations

    the term "actual" and its variations in different contexts

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

    "actual" followed by context words

    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
    inghouse
    -0.59
    ofor
    -0.54
    ɜ
    -0.51
    ofür
    -0.49
    Forgery
    -0.48
    zuführen
    -0.48
     Houſe
    -0.47
    Forge
    -0.47
    BERG
    -0.47
    nologies
    -0.47
    POSITIVE LOGITS
    actual
    1.89
    Actual
    1.87
     Actual
    1.73
     actual
    1.72
     ACTUAL
    1.63
    ACTUAL
    1.59
    actually
    1.06
    实际
    1.05
     actually
    0.98
     tatsäch
    0.96
    Activations Density 0.006%

    No Known Activations