© 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. 11279
    Prev
    Next
    INDEX
    Explanations

    terms related to comprehensive analysis and research methodologies

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

    ending in "sion", "sive", "ding", or "sible"

    np_acts-logits-general · gemini-2.0-flash

    -sions / -sive / -sibility

    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
    TestBed
    -0.64
     дописавши
    -0.58
    WebElementEntity
    -0.52
    IUrlHelper
    -0.52
     esquema
    -0.47
    یه
    -0.47
    AsUp
    -0.45
    Földrajzportál
    -0.45
    Vidite
    -0.44
    انيف
    -0.43
    POSITIVE LOGITS
    sions
    1.01
     sion
    0.95
    sively
    0.91
    sive
    0.84
    siv
    0.83
    sion
    0.78
    sives
    0.78
    sional
    0.78
    sión
    0.78
    siveness
    0.78
    Activations Density 0.238%

    No Known Activations