© 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. 21-GEMMASCOPE-RES-16K
    6. 8734
    Prev
    Next
    INDEX
    Explanations

    descriptions of past events or states related to performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (;;)
    -0.60
     conci
    -0.55
    yarnpkg
    -0.55
     existente
    -0.54
    inthians
    -0.52
     erreich
    -0.52
    potranspiration
    -0.51
     intelligence
    -0.51
     qashqai
    -0.51
    Rhestr
    -0.50
    POSITIVE LOGITS
    :✨
    0.74
    ValueStyle
    0.73
    StoryboardSegue
    0.67
     hot
    0.61
    UnusedPrivate
    0.61
     unstoppable
    0.59
     Roskov
    0.58
    tvguidetime
    0.57
    脚注の使い方
    0.56
     dominant
    0.55
    Activations Density 0.127%

    No Known Activations