© 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. 13057
    Prev
    Next
    INDEX
    Explanations

    legal obligations and failures to comply with orders

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

    phrases expressing failure to comply with legal obligations or court orders.

    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
    ScopeManager
    -0.55
     typelib
    -0.53
     مرئيه
    -0.52
    AndEndTag
    -0.49
    newtheorem
    -0.47
    MigrationBuilder
    -0.47
    kali
    -0.46
    EndContext
    -0.45
    tonode
    -0.45
    AsUp
    -0.44
    POSITIVE LOGITS
     obey
    0.69
     abide
    0.65
     comply
    0.65
     report
    0.57
     compliance
    0.55
     obeyed
    0.54
     pay
    0.54
     submit
    0.53
     cooperate
    0.52
     obeys
    0.52
    Activations Density 0.700%

    No Known Activations