© 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. 7-GEMMASCOPE-RES-16K
    11. 12851
    Prev
    Next
    INDEX
    Explanations

    sections of text that indicate experimental or research design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.87
    PreferredItem
    -0.84
    adaptiveStyles
    -0.84
    RegressionTest
    -0.81
    uxxxx
    -0.79
     kasarigan
    -0.73
    fjspx
    -0.72
    tonode
    -0.71
     nakalista
    -0.71
    PostInfinity
    -0.70
    POSITIVE LOGITS
     organized
    0.33
    IntoConstraints
    0.33
     ș
    0.32
     Ward
    0.29
     free
    0.29
    発
    0.28
    “
    0.28
     W
    0.28
     taking
    0.28
     protected
    0.28
    Activations Density 0.510%

    No Known Activations