© 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. 4555
    Prev
    Next
    INDEX
    Explanations

    HTML code elements and attributes

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

    HTML and web development markup and code structure elements.

    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
     SqlCommand
    -0.32
    Bindable
    -0.31
    齣
    -0.29
     button
    -0.28
    <tfoot>
    -0.28
    ModelForm
    -0.28
    ç
    -0.28
    ịch
    -0.27
     plus
    -0.27
     põ
    -0.27
    POSITIVE LOGITS
    Rüyada
    0.69
    хьтан
    0.68
    Autoritní
    0.65
    PMailer
    0.63
     informée
    0.62
     للمعارف
    0.61
     ſind
    0.61
     ویکی‌پدی
    0.60
     OFDb
    0.58
     pleaſure
    0.57
    Activations Density 0.023%

    No Known Activations