© 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. 8706
    Prev
    Next
    INDEX
    Explanations

    names of institutions and people involved in academic or professional settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    daß
    -0.69
    hitheater
    -0.65
     econô
    -0.63
     mustache
    -0.63
     uș
    -0.62
     grayish
    -0.62
     gewiß
    -0.62
    ɚ
    -0.61
    inephrine
    -0.60
     creș
    -0.60
    POSITIVE LOGITS
     (£
    1.03
     £
    0.94
     UK
    0.92
    -£
    0.88
    UK
    0.81
     HMRC
    0.75
     NHS
    0.74
    £
    0.74
    Whilst
    0.73
     whilst
    0.71
    Activations Density 1.401%

    No Known Activations