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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8640
    Prev
    Next
    INDEX
    Explanations

    terms related to interpretation and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.59
    DotNetBar
    -0.57
     obicei
    -0.46
    Πηγές
    -0.45
     casinos
    -0.43
     kosme
    -0.43
     sàng
    -0.43
    posedge
    -0.42
    BASELINE
    -0.42
     sûr
    -0.41
    POSITIVE LOGITS
     interpretation
    2.81
     interpret
    2.77
     Interpretation
    2.58
     interpreted
    2.56
    interpretation
    2.52
     Interpret
    2.50
     INTERPRET
    2.50
     interpretations
    2.50
     interpreting
    2.48
    interpret
    2.45
    Activations Density 0.080%

    No Known Activations