© 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. 3-GEMMASCOPE-RES-16K
    11. 8131
    Prev
    Next
    INDEX
    Explanations

    instances of the word "impose" and its variations in discussing regulations or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MethodManager
    -0.52
     obstacles
    -0.44
    obstacles
    -0.40
    ScopeManager
    -0.40
    stacles
    -0.39
    蚪
    -0.38
    RTLR
    -0.37
    TargetApi
    -0.36
    abetes
    -0.36
    hurt
    -0.36
    POSITIVE LOGITS
     imposed
    1.35
     imposition
    1.34
     impose
    1.31
     imposing
    1.23
     restriction
    1.23
     restrictions
    1.22
     constraint
    1.14
     imposes
    1.09
     Restrictions
    1.08
     constraints
    1.05
    Activations Density 0.078%

    No Known Activations