© 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. 0-GEMMASCOPE-RES-16K
    11. 8758
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their anatomical 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 @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Verſ
    -0.61
    THISDAY
    -0.55
     ProtoMessage
    -0.54
    ScopeManager
    -0.52
    FieldBuilder
    -0.51
    もしろ
    -0.50
     становника
    -0.49
    نص
    -0.49
     Anſ
    -0.49
     كومونز
    -0.49
    POSITIVE LOGITS
     Kur
    0.44
     sac
    0.41
     escapar
    0.41
     problematic
    0.38
     scar
    0.38
    ect
    0.38
     escape
    0.38
     eject
    0.38
     prospect
    0.37
    Kur
    0.36
    Activations Density 1.680%

    No Known Activations