© 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. 24-GEMMASCOPE-RES-16K
    11. 14431
    Prev
    Next
    INDEX
    Explanations

    specific keywords related to data, programming, and technology

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

    Tokens followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    words ending in 'e' followed by numbers or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ness
    -1.49
    nya
    -1.34
    name
    -0.96
    sy
    -0.83
    d
    -0.81
    sa
    -0.80
    not
    -0.80
    night
    -0.80
    so
    -0.79
    了
    -0.78
    POSITIVE LOGITS
    e
    0.58
    eeee
    0.57
    eeeeeeee
    0.54
    eeeee
    0.50
    eee
    0.49
    eeeeee
    0.45
    ee
    0.44
     mergeFrom
    0.41
    lectron
    0.40
    lets
    0.40
    Activations Density 2.058%

    No Known Activations