© 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. 2503
    Prev
    Next
    INDEX
    Explanations

    descriptions of items or entities that highlight their appealing qualities and suitability for specific purposes

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

    Preceding words of "ideal."

    np_acts-logits-general · gemini-2.0-flash

    ideal and perfect

    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
     Biôgrafia
    -0.73
    onViewCreated
    -0.72
    GEBURTSDATUM
    -0.72
    Personendaten
    -0.72
    AndEndTag
    -0.71
    ValueStyle
    -0.70
    Хьажоргаш
    -0.70
     ostavi
    -0.69
    titleMargin
    -0.68
    +#+#
    -0.66
    POSITIVE LOGITS
     ideal
    2.10
     perfect
    2.07
     suitable
    1.81
    ideal
    1.76
    perfect
    1.73
    Ideal
    1.63
     great
    1.62
     Ideal
    1.57
     ideale
    1.54
     ideales
    1.53
    Activations Density 0.278%

    No Known Activations