© 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. 2040
    Prev
    Next
    INDEX
    Explanations

    technical programming concepts and procedures

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

    Spanish articles (el, la, los, las)

    np_acts-logits-general · gemini-2.0-flash

    Spanish articles and prepositions

    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
    KURZBESCHREIBUNG
    -0.52
    oop
    -0.52
     NSCoder
    -0.47
    Clik
    -0.45
     оригіналу
    -0.44
     you
    -0.44
    Források
    -0.43
     itself
    -0.42
     Selv
    -0.41
    KommentareTeilen
    -0.41
    POSITIVE LOGITS
     la
    1.78
     el
    1.66
     las
    1.27
     los
    1.18
     su
    1.09
     els
    0.93
     una
    0.85
     sus
    0.83
     toda
    0.83
     nuestra
    0.82
    Activations Density 0.035%

    No Known Activations