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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10407
    Prev
    Next
    INDEX
    Explanations

    references to the term "Gri" and its variations

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

    "Gri" followed by characters

    np_acts-logits-general · gemini-2.0-flash

    words starting with Gri

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.83
    clable
    -0.76
     فريبيس
    -0.70
    LookAnd
    -0.69
     AssemblyProduct
    -0.67
    +:+
    -0.67
    prefixer
    -0.66
    Controllo
    -0.64
    شهاد
    -0.63
    Personensuche
    -0.63
    POSITIVE LOGITS
     Gri
    1.23
    Gri
    1.15
     gri
    1.01
    gri
    0.88
    Гри
    0.84
     гри
    0.75
     grids
    0.74
    グリ
    0.72
    grids
    0.71
     Grizzlies
    0.71
    Activations Density 0.130%

    No Known Activations