© 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. 3523
    Prev
    Next
    INDEX
    Explanations

    phrases related to nominations and awards

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

    Nomination, selection, or shortlisting

    np_acts-logits-general · gemini-2.0-flash

    nominees and finalists for awards

    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
    RegressionTest
    -0.44
     {}
    -0.43
    ורים
    -0.42
     considérons
    -0.42
    казания
    -0.41
    ರೆ
    -0.40
    addPreferredGap
    -0.40
    marriage
    -0.40
    ba
    -0.40
    ilmente
    -0.40
    POSITIVE LOGITS
     finalists
    1.54
     finalist
    1.35
     shortlist
    1.30
     shortlisted
    1.27
     nominees
    1.16
     nominee
    1.09
     semifinal
    1.02
     candidate
    0.90
     nominated
    0.90
     candidates
    0.88
    Activations Density 0.269%

    No Known Activations