© 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. 5-GEMMASCOPE-RES-16K
    11. 13697
    Prev
    Next
    INDEX
    Explanations

    words indicating management, evaluation, or oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.71
    stals
    -0.71
    <h2>
    -0.71
    ghed
    -0.67
    pezi
    -0.66
    erals
    -0.63
     aasta
    -0.58
    chestra
    -0.57
    Clik
    -0.57
     weakly
    -0.56
    POSITIVE LOGITS
     thereof
    0.91
     ensued
    0.87
    ()]
    0.84
    wixt
    0.84
     locale
    0.83
    virons
    0.82
     obstante
    0.82
     szóci
    0.82
     lediglich
    0.82
     تضيفلها
    0.80
    Activations Density 2.035%

    No Known Activations