© 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. 76733
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering or receiving advice

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

    advice and guidance

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects tokens and short phrases that indicate requests for or the offering of advice, tips, or suggestions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    literals
    -0.52
    ="@+
    -0.46
    endphp
    -0.44
    CrossRef
    -0.40
     BorderSide
    -0.39
    didSet
    -0.39
    CopyWith
    -0.39
    RepeatedField
    -0.37
    \{\\
    -0.37
     للاسماء
    -0.37
    POSITIVE LOGITS
     advice
    1.26
     Advice
    1.08
     ADVICE
    1.05
    advice
    1.03
    Advice
    1.02
     consejos
    1.00
     advise
    0.96
    Consejos
    0.90
     advises
    0.87
     advices
    0.87
    Activations Density 0.123%

    No Known Activations