© 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. 18-GEMMASCOPE-RES-16K
    11. 14756
    Prev
    Next
    INDEX
    Explanations

    key terms related to significant historical events and official documents

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

    that often follow nouns indicating time or sequence

    np_acts-logits-general · gemini-2.0-flash

    after a period or war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.87
     CreateTagHelper
    -0.73
    mergeFrom
    -0.68
    +#+
    -0.64
    adaptiveStyles
    -0.64
     myſelf
    -0.64
    DataAnnotations
    -0.63
    SequentialGroup
    -0.63
    DockStyle
    -0.62
     propOrder
    -0.62
    POSITIVE LOGITS
     became
    0.82
     becomes
    0.77
     came
    0.77
     has
    0.75
     began
    0.75
     had
    0.73
     comes
    0.72
     arrives
    0.71
     finishes
    0.68
     begins
    0.66
    Activations Density 0.270%

    No Known Activations