© 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. 28-GEMMASCOPE-RES-16K
    11. 8405
    Prev
    Next
    INDEX
    Explanations

    references to policies and frameworks related to governance and legal matters

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

    "policy"

    np_acts-logits-general · gemini-2.0-flash

    policy, rules, and enforcement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bénévol
    -0.52
     navidad
    -0.46
     pitié
    -0.46
     Demokratie
    -0.45
    orElseThrow
    -0.43
     femininas
    -0.43
     Turquía
    -0.42
     navideño
    -0.41
     movilidad
    -0.41
     économ
    -0.41
    POSITIVE LOGITS
    CppMethod
    0.68
     Policy
    0.64
     enforcement
    0.63
     policy
    0.61
     nahilalakip
    0.60
     Enforcement
    0.57
     Rule
    0.57
     enforced
    0.56
     &___
    0.56
    enschappelijke
    0.56
    Activations Density 0.627%

    No Known Activations