Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 794
    Prev
    Next
    INDEX
    Explanations

    details related to player statistics and achievements in sports

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

    Scoring statistics or numbers

    np_acts-logits-general · gemini-2.0-flash

    scoring and points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.61
    Produkte
    -0.57
    alahkan
    -0.57
    Nachteile
    -0.57
    sidemargin
    -0.57
    andafter
    -0.56
     aerop
    -0.55
    harusnya
    -0.54
     calendriers
    -0.53
     JUGA
    -0.53
    POSITIVE LOGITS
    ⓧ
    0.79
     plenty
    0.63
     six
    0.59
     four
    0.58
     two
    0.57
    tvguidetime
    0.56
    脚注の使い方
    0.56
    migrationBuilder
    0.55
    queryInterface
    0.55
     three
    0.54
    Activations Density 0.166%

    No Known Activations