© 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. 10-GEMMASCOPE-RES-16K
    11. 4182
    Prev
    Next
    INDEX
    Explanations

    phrases that express the need or intention to evade or prevent certain actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $_(
    -0.67
    ientras
    -0.64
     AssemblyCompany
    -0.63
     $_"
    -0.62
     AssemblyVersion
    -0.60
     purpoſe
    -0.60
     packageName
    -0.59
    IntoConstraints
    -0.59
    URLException
    -0.58
    ReusableCell
    -0.57
    POSITIVE LOGITS
     avoid
    1.65
    avoid
    1.59
     avoiding
    1.57
    Avoid
    1.56
     avoided
    1.53
     Avoid
    1.52
     avoidance
    1.51
     AVOID
    1.50
     avoids
    1.50
    Avoiding
    1.39
    Activations Density 0.155%

    No Known Activations