© 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. 9-GEMMASCOPE-RES-16K
    11. 9876
    Prev
    Next
    INDEX
    Explanations

    terms related to visibility and concealment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pragma
    -0.80
    amssymb
    -0.49
    ActionPerformed
    -0.43
    findpost
    -0.42
    addGap
    -0.42
    <bos>
    -0.36
     plans
    -0.34
    assertRaises
    -0.33
    addGroup
    -0.33
    BorderFactory
    -0.32
    POSITIVE LOGITS
     hidden
    2.41
    hidden
    2.31
     Hidden
    2.14
    Hidden
    2.11
    HIDDEN
    1.65
     verborgen
    1.46
    隐藏
    1.45
     ukry
    1.44
     скры
    1.41
     concealed
    1.40
    Activations Density 0.052%

    No Known Activations