© 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. 3-GEMMASCOPE-RES-16K
    11. 8547
    Prev
    Next
    INDEX
    Explanations

    identifiers and metrics commonly associated with academic references and publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :+:
    -0.76
    Билгалдахарш
    -0.67
    moveToFirst
    -0.65
     jsPsych
    -0.65
    #+#
    -0.61
     ricevuto
    -0.61
    jupiter
    -0.60
    ्रीय
    -0.60
    saraba
    -0.59
     skimage
    -0.56
    POSITIVE LOGITS
     ISBN
    1.23
    ISBN
    1.19
    Locale
    0.89
    Autoritní
    0.82
     isbn
    0.79
    ASSERT
    0.77
     ISNI
    0.76
    isbn
    0.73
     Locale
    0.72
     Normdatei
    0.69
    Activations Density 0.010%

    No Known Activations