© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12744
    Prev
    Next
    INDEX
    Explanations

    key terms related to inspections and evaluations in construction contexts

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

    inspections or engineers

    np_acts-logits-general · gemini-2.0-flash

    inspection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.63
    onOptions
    -0.58
    LEncoder
    -0.55
    MethodManager
    -0.49
    EDEFAULT
    -0.49
     GenerationType
    -0.49
    jectories
    -0.48
    throwaway
    -0.47
    disambiguation
    -0.46
    GOTREF
    -0.46
    POSITIVE LOGITS
     inspection
    2.11
     inspections
    1.98
     Inspection
    1.91
     inspecting
    1.87
     inspectors
    1.86
     Inspections
    1.80
    Inspection
    1.79
     inspect
    1.71
     INSPECTION
    1.69
    inspection
    1.69
    Activations Density 0.312%

    No Known Activations