Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14716
    Prev
    Next
    INDEX
    Explanations

    references to governmental intervention in various contexts

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

    Variations of "intervene"

    np_acts-logits-general · gemini-2.0-flash

    step in or get involved

    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
    SharedDtor
    -0.46
     pulsa
    -0.45
    lead
    -0.42
    ErrUnexpectedEOF
    -0.41
     faim
    -0.41
     Signalez
    -0.41
    hatsu
    -0.40
     према
    -0.40
     salariés
    -0.39
    +#+#
    -0.39
    POSITIVE LOGITS
     intervene
    2.21
     intervention
    2.02
     intervened
    2.02
     interven
    1.85
     intervening
    1.83
     intervenir
    1.73
    intervention
    1.73
    Intervention
    1.70
     Intervention
    1.70
    介入
    1.60
    Activations Density 0.373%

    No Known Activations