© 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. 1685
    Prev
    Next
    INDEX
    Explanations

    historical references and foundations of institutions

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

    creation or establishment

    np_acts-logits-general · gemini-2.0-flash

    founding and creation

    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
    annica
    -0.66
    Mediabestanden
    -0.55
    ayne
    -0.52
     estekak
    -0.50
    bootstrapcdn
    -0.50
     препратки
    -0.48
    webElementGuid
    -0.48
    Datuak
    -0.48
    thodes
    -0.48
    quième
    -0.48
    POSITIVE LOGITS
     founding
    1.63
     creation
    1.41
     founded
    1.40
     founders
    1.32
     creating
    1.29
     création
    1.27
     create
    1.27
     Gründung
    1.26
     created
    1.25
     founder
    1.24
    Activations Density 0.431%

    No Known Activations