© 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. 4760
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or theoretical concepts, particularly those involving functions and structures

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

    German or Japanese text fragments

    np_acts-logits-general · gemini-2.0-flash

    qualified, precipitated, placed, divided

    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
    ьаж
    -0.84
    RegistryLite
    -0.80
    tagHelperRunner
    -0.77
     Wikimedijinoj
    -0.72
    OrBuilder
    -0.68
    AndEndTag
    -0.67
     оригіналу
    -0.65
    Билгалдахарш
    -0.64
     ویکی‌پدی
    -0.63
    InjectAttribute
    -0.62
    POSITIVE LOGITS
     olev
    0.61
     した
    0.56
    된
    0.55
    された
    0.55
    isting
    0.53
     된
    0.53
    した
    0.52
    tifiz
    0.51
     olmayan
    0.49
    ATED
    0.48
    Activations Density 0.076%

    No Known Activations