© 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. 9-GEMMASCOPE-RES-16K
    11. 13199
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing specific conditions or situations

    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
    formKey
    -0.52
     armées
    -0.49
    bonucle
    -0.48
     ferons
    -0.45
     BoxDecoration
    -0.45
     Houſe
    -0.45
     pouvoit
    -0.44
    擺
    -0.44
     bureaux
    -0.44
    Toilet
    -0.43
    POSITIVE LOGITS
     especially
    2.11
    Especially
    2.02
     Especially
    1.98
    especially
    1.91
     particularly
    1.70
     especialmente
    1.63
     Particularly
    1.60
    particularly
    1.57
     особенно
    1.53
     Особенно
    1.52
    Activations Density 0.114%

    No Known Activations