© 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. 16-GEMMASCOPE-RES-16K
    11. 9242
    Prev
    Next
    INDEX
    Explanations

    specific names and references to individuals and relationships

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

    Arrivals or arriving entities

    np_acts-logits-general · gemini-2.0-flash

    arrival / visiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\..\
    -0.57
    Décès
    -0.55
     "..\..\
    -0.54
    EndGlobalSection
    -0.51
    TypedDataSet
    -0.51
    går
    -0.51
     toss
    -0.50
    setVerticalGroup
    -0.50
    NOPQRST
    -0.49
    ற்ப
    -0.49
    POSITIVE LOGITS
     arriving
    1.40
     arrival
    1.26
     arrives
    1.17
     arrived
    1.15
     arrive
    1.14
     visiting
    1.10
    Arri
    1.10
     arrivals
    1.09
     datang
    1.08
     visitors
    1.07
    Activations Density 0.485%

    No Known Activations