© 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. 1980
    Prev
    Next
    INDEX
    Explanations

    legal terminology and conditions related to agreements and policies

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

    legal and policy agreement language, particularly terms and conditions that users must accept or comply with.

    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
     INSEE
    -0.36
    Insee
    -0.34
     Betracht
    -0.32
    ILogger
    -0.30
    umoj
    -0.30
     machete
    -0.30
    alternatives
    -0.29
    InlineData
    -0.29
    SupportActionBar
    -0.29
    ctrica
    -0.28
    POSITIVE LOGITS
     Terms
    1.20
     terms
    1.09
    Terms
    1.08
     rules
    1.03
     TERMS
    1.00
     Rules
    0.98
    terms
    0.98
    Rules
    0.97
    RULES
    0.96
    rules
    0.96
    Activations Density 0.414%

    No Known Activations