© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1020
    Prev
    Next
    INDEX
    Explanations

    phrases or references related to education and academic credentials

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

    years and dates, especially years from the late 1800s and early 1900s.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    Chham
    -0.80
     שוליים
    -0.59
    rrggbb
    -0.59
     disponibilités
    -0.59
     ujednoznacz
    -0.57
    তথ্যসূত্র
    -0.56
     occaf
    -0.56
     الرياضيه
    -0.54
     internetowa
    -0.54
    DataAnnotations
    -0.54
    POSITIVE LOGITS
     became
    0.48
     subsequently
    0.44
    became
    0.41
     grew
    0.40
     later
    0.40
     initially
    0.38
     originally
    0.37
    later
    0.35
     began
    0.35
    当時は
    0.35
    Activations Density 0.274%

    No Known Activations