© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15755
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to heavy elements and their properties

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

    chemical element symbols like H (hydrogen) and scientific terms like HaloFit.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    endcsname
    -0.66
    thâu
    -0.53
     للاسماء
    -0.52
    mybatisplus
    -0.50
    intios
    -0.50
    PRNewswire
    -0.49
    Spoljašnje
    -0.46
    ⮕
    -0.45
     betweenstory
    -0.45
     
    -0.44
    POSITIVE LOGITS
     H
    0.88
    H
    0.84
    h
    0.76
     h
    0.71
    setH
    0.70
     nadzie
    0.69
    HB
    0.67
    ฮ
    0.66
    hb
    0.65
    hf
    0.65
    Activations Density 1.055%

    No Known Activations