© 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. 1-GEMMASCOPE-RES-16K
    6. 7199
    Prev
    Next
    INDEX
    Explanations

    Java input/output operations and related classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ykite
    -0.61
    lehre
    -0.59
     Venise
    -0.59
    Сыртқы
    -0.58
    teborg
    -0.58
    Cuánto
    -0.57
     lika
    -0.57
    acier
    -0.56
     universal
    -0.55
    Voci
    -0.53
    POSITIVE LOGITS
     در
    1.16
    tre
    1.01
    در
    1.00
     Tam
    0.95
    Tam
    0.95
    Tre
    0.95
     tam
    0.91
     tre
    0.85
     Tre
    0.80
     DRE
    0.76
    Activations Density 0.094%

    No Known Activations