© 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. 2520
    Prev
    Next
    INDEX
    Explanations

    HTML and class attributes in a document

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

    HTML class or type attributes

    np_acts-logits-general · gemini-2.0-flash

    attribute assignments in code

    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
     دیکھیے
    -0.67
    はじめに
    -0.61
    ldre
    -0.60
     faciles
    -0.60
    saraba
    -0.59
     ویکی‌پدی
    -0.57
     ejus
    -0.57
     väh
    -0.57
    Tazama
    -0.56
    indest
    -0.55
    POSITIVE LOGITS
     محفوظة
    0.71
    dow
    0.63
    httphttps
    0.63
     AssemblyTitle
    0.59
    TagHelper
    0.57
     виправивши
    0.56
     defaultstate
    0.55
    HomeAsUpEnabled
    0.51
     saites
    0.51
    migrationBuilder
    0.51
    Activations Density 0.082%

    No Known Activations