© 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. 22-GEMMASCOPE-RES-16K
    11. 8123
    Prev
    Next
    INDEX
    Explanations

    quantifiable data and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "every" or "each"

    np_acts-logits-general · gemini-2.0-flash

    for every

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikum
    -0.52
    TestingModule
    -0.51
    extAlignment
    -0.49
    OTROS
    -0.48
    этому
    -0.47
     Others
    -0.47
    Others
    -0.47
    VersionUID
    -0.47
     transférez
    -0.47
     allemaal
    -0.46
    POSITIVE LOGITS
     every
    3.24
    every
    2.76
     Every
    2.53
    Every
    2.53
     ogni
    2.08
     EVERY
    2.06
     setiap
    1.98
     chaque
    1.86
     varje
    1.79
    EVERY
    1.77
    Activations Density 0.410%

    No Known Activations