© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 707
    Prev
    Next
    INDEX
    Explanations

    bracketed elements and references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [toxicity=0]
    -0.65
    <h1>
    -0.28
    ntä
    -0.28
    vedať
    -0.28
    \
    -0.27
    The
    -0.26
    <h3>
    -0.25
      
    -0.24
    <h2>
    -0.24
    Abit
    -0.24
    POSITIVE LOGITS
     виправивши
    1.02
     tartalomajánló
    1.00
     للاسماء
    0.98
     defaultstate
    0.95
    UnusedPrivate
    0.90
    RenderAtEndOf
    0.90
    تقاوى
    0.90
    MessageOf
    0.88
    +#+#
    0.86
     noDo
    0.85
    Activations Density 0.506%

    No Known Activations