© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8008
    Prev
    Next
    INDEX
    Explanations

    phrases related to error messages and user profiles

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

    Galician or Spanish language

    np_acts-logits-general · gemini-2.0-flash

    follows 'o', 'da', 'de', '{\', '4', 'would'

    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
    mybatisplus
    -0.74
    kuuta
    -0.66
    KommentareTeilen
    -0.64
     lenker
    -0.63
     ---
    -0.57
    BeginInit
    -0.56
    HasForeignKey
    -0.56
     ویکی‌پدیای
    -0.54
    queryInterface
    -0.53
     makeStyles
    -0.52
    POSITIVE LOGITS
     máis
    0.56
    Trax
    0.56
    Véxase
    0.56
     xa
    0.54
     moi
    0.53
     xe
    0.51
     mell
    0.51
     unha
    0.51
     garda
    0.49
     Roskov
    0.48
    Activations Density 0.079%

    No Known Activations