© 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. 31-GEMMASCOPE-RES-131K
    11. 65614
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize benefits or advantages in various contexts

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

    advantage and disadvantages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sheeran
    -0.39
     dataSnapshot
    -0.38
    Foreign
    -0.38
    cks
    -0.38
    Indian
    -0.37
     Enfer
    -0.37
     transfieras
    -0.36
    setNum
    -0.36
     FBref
    -0.36
    uarine
    -0.36
    POSITIVE LOGITS
     Advantage
    0.71
     disadvantages
    0.71
    ANTAGE
    0.70
     Advantages
    0.69
     disadvantage
    0.68
     advantage
    0.66
     Disadvantages
    0.65
    RegressionTest
    0.65
     advantages
    0.65
    vantage
    0.64
    Activations Density 0.012%

    No Known Activations