© 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. 5-GEMMASCOPE-RES-16K
    6. 10747
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation, particularly related to set notation and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lähteet
    -0.75
    ագրություններ
    -0.57
    ↵↵↵
    -0.57
    abestanden
    -0.54
    <bos>
    -0.51
    SuppressLint
    -0.50
    umbra
    -0.48
    ponte
    -0.48
    __);
    -0.47
     Relatives
    -0.46
    POSITIVE LOGITS
    بوابة
    0.71
    HasForeignKey
    0.66
     '\\;'
    0.66
     مُعرِّف
    0.66
     déput
    0.62
    Portail
    0.61
    حياته
    0.61
    vgili
    0.58
     SYLLABLE
    0.57
     Gattung
    0.57
    Activations Density 0.812%

    No Known Activations