© 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. 38273
    Prev
    Next
    INDEX
    Explanations

    the concept of balance between contrasting elements or ideas

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

    balance between

    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
     ་་
    -0.51
     Shortcuts
    -0.49
     Efq
    -0.49
    ICEF
    -0.49
     ſei
    -0.48
     chofe
    -0.48
     myſelf
    -0.48
    principalColumn
    -0.48
    theless
    -0.48
     Cores
    -0.47
    POSITIVE LOGITS
     delicate
    0.85
     balance
    0.84
     balancing
    0.82
     delicately
    0.77
     tricky
    0.77
     BALANCE
    0.69
     difficult
    0.69
     балан
    0.67
    balance
    0.66
    Balance
    0.66
    Activations Density 0.059%

    No Known Activations