© 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. 11-GEMMASCOPE-RES-16K
    11. 12778
    Prev
    Next
    INDEX
    Explanations

    references to profiles and profile-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     démocr
    -0.54
     rubber
    -0.50
     bakteri
    -0.49
     feroit
    -0.49
     almacenamiento
    -0.48
     zieken
    -0.48
     voulons
    -0.48
     mathématiques
    -0.48
     goederen
    -0.48
    música
    -0.48
    POSITIVE LOGITS
     profile
    2.13
     profiles
    1.94
     Profile
    1.94
    profile
    1.84
    Profile
    1.80
     PROFILE
    1.79
     Profiles
    1.75
    PROFILE
    1.62
    Profiles
    1.57
     profil
    1.51
    Activations Density 0.135%

    No Known Activations