© 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. 12715
    Prev
    Next
    INDEX
    Explanations

    phrases indicating varying degrees or amounts, particularly those involving "little" or "bit"

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

    "Bit" or "little" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    a bit or little bit followed by degree

    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
     незавершена
    -0.90
     Pingback
    -0.80
     pauv
    -0.67
    \{\\
    -0.67
    makeConstraints
    -0.66
    ⋙
    -0.66
     الحره
    -0.66
     efficacement
    -0.64
    indd
    -0.61
    excellents
    -0.61
    POSITIVE LOGITS
     bit
    1.10
    ValueStyle
    0.72
    bit
    0.72
     more
    0.70
    Bit
    0.69
     BIT
    0.66
     longer
    0.66
     higher
    0.66
     too
    0.65
    tagext
    0.64
    Activations Density 0.112%

    No Known Activations