© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2174
    Prev
    Next
    INDEX
    Explanations

    terms related to geological surveys and psychological factors

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

    The neuron detects the word "psychological" especially when it appears in academic or medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "Psychological" regardless of context.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     noDo
    -0.69
    EndContext
    -0.65
     الرياضيه
    -0.60
     فريبيس
    -0.60
     الحره
    -0.59
     estekak
    -0.58
    Tikang
    -0.57
     EconPapers
    -0.57
    arangay
    -0.56
     برانيه
    -0.54
    POSITIVE LOGITS
     study
    0.40
    学家
    0.40
    ább
    0.39
     Gottlieb
    0.35
    foreignKey
    0.35
    quement
    0.34
     viewpoint
    0.34
    /
    0.34
     standard
    0.34
     society
    0.33
    Activations Density 0.348%

    No Known Activations