© 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. 22-GEMMASCOPE-RES-16K
    6. 14733
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives indicating magnitude, size, or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ━
    -0.57
    etCode
    -0.54
     Joachim
    -0.53
    ﴿
    -0.53
     Guill
    -0.52
     Keim
    -0.51
     WIND
    -0.50
     Cyclo
    -0.50
    \]
    -0.49
     photo
    -0.49
    POSITIVE LOGITS
    faster
    0.73
    easier
    0.68
    longer
    0.67
    Faster
    0.66
    higher
    0.65
     betweenstory
    0.65
    larger
    0.64
     Stronger
    0.63
     Smarter
    0.63
    asier
    0.62
    Activations Density 0.235%

    No Known Activations