© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 8809
    Prev
    Next
    INDEX
    Explanations

    phrases related to police collaboration and sharing of information

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

    phrases describing the exchange or sharing of information, ideas, and knowledge among groups or organizations.

    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
     Autorizaciones
    -0.33
    vician
    -0.32
     requer
    -0.31
     Addition
    -0.31
    exitRule
    -0.31
    hasMoreElements
    -0.30
    대로
    -0.30
    esgue
    -0.30
    ViewInit
    -0.30
     Shiv
    -0.30
    POSITIVE LOGITS
     exchange
    2.63
     exchanging
    2.41
     exchanged
    2.30
    exchange
    2.27
    Exchange
    2.13
     EXCHANGE
    2.13
     exchanges
    2.11
     intercambio
    2.05
     Exchange
    1.97
    EXCHANGE
    1.91
    Activations Density 0.392%

    No Known Activations