Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 2362
    Prev
    Next
    INDEX
    Explanations

    terms related to regional offices and organizational structures within unions or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TargetException
    -0.66
    IsRequired
    -0.53
    aji
    -0.50
    addFlags
    -0.49
     subscript
    -0.48
    ERP
    -0.48
    oader
    -0.48
    nestjs
    -0.48
    lassi
    -0.48
     Ove
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.78
     regionales
    0.74
     regionale
    0.73
     District
    0.73
     setempat
    0.71
     régionale
    0.70
     régional
    0.69
     district
    0.69
    errHandler
    0.69
    District
    0.66
    Activations Density 0.310%

    No Known Activations