© 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. 6360
    Prev
    Next
    INDEX
    Explanations

    terms related to strictness and rigorousness, particularly in legal or procedural contexts

    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
    InjectAttribute
    -0.50
     vapors
    -0.47
    unexpected
    -0.46
     faune
    -0.44
     unexpected
    -0.44
     vindo
    -0.44
    Unexpected
    -0.43
    QMetaType
    -0.43
    vapor
    -0.43
     Verbraucher
    -0.43
    POSITIVE LOGITS
     strict
    0.77
     Strict
    0.68
     Instruction
    0.66
    instruction
    0.64
     Olive
    0.62
     instruction
    0.62
    strict
    0.62
     Miss
    0.60
     rigorous
    0.60
    Instruction
    0.60
    Activations Density 0.121%

    No Known Activations