© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 157
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the future tense or planned actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     successes
    -0.63
    agree
    -0.62
    verwijspagina
    -0.62
     réuss
    -0.62
     agree
    -0.61
     conviction
    -0.60
     moschino
    -0.60
     aseguran
    -0.60
     Audiodateien
    -0.59
     aprobó
    -0.59
    POSITIVE LOGITS
     host
    0.59
     محفوظة
    0.53
    CloseOperation
    0.53
    のではなく
    0.50
     debut
    0.49
     auction
    0.47
     hosting
    0.47
     officially
    0.47
     चीज़ों
    0.47
     joining
    0.46
    Activations Density 0.221%

    No Known Activations