© 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. 13-GEMMASCOPE-RES-16K
    6. 7984
    Prev
    Next
    INDEX
    Explanations

    sequences of letters or characters that may indicate alphanumeric patterns or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.79
     otomatig
    -0.78
     }}"></
    -0.77
    PLAUSE
    -0.75
    ("]");
    -0.75
    CloseOperation
    -0.74
    cody
    -0.74
    bosity
    -0.72
    تقاوى
    -0.72
    >");
    
    -0.71
    POSITIVE LOGITS
    Kaynakça
    0.78
    SizeF
    0.67
    withstanding
    0.62
     dàng
    0.59
    XmlEnum
    0.57
     dotyczy
    0.57
     Cæsar
    0.56
     Silurian
    0.56
    Przypisy
    0.55
     DCM
    0.55
    Activations Density 0.548%

    No Known Activations