© 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. 2122
    Prev
    Next
    INDEX
    Explanations

    words and phrases that indicate inquiry or discussion about various subjects

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

    Questions starting with "about"

    np_acts-logits-general · gemini-2.0-flash

    discussing topics or questions

    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
     они
    -0.52
     réguli
    -0.52
     trouverez
    -0.51
    they
    -0.49
     fixé
    -0.48
     cortas
    -0.47
     they
    -0.46
     verrez
    -0.46
     она
    -0.45
    demás
    -0.45
    POSITIVE LOGITS
     how
    1.68
     why
    1.53
     whether
    1.19
     what
    1.16
    why
    1.12
     cómo
    1.02
     WHY
    0.98
    how
    0.98
    如何
    0.92
     bagaimana
    0.92
    Activations Density 0.351%

    No Known Activations