© 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. 7521
    Prev
    Next
    INDEX
    Explanations

    questions and references related to identity and relationships between people

    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
     parallel
    -0.44
     simple
    -0.43
     part
    -0.40
     primitive
    -0.40
     It
    -0.39
     şekilde
    -0.39
     esche
    -0.38
    制
    -0.38
     its
    -0.38
     Galloway
    -0.37
    POSITIVE LOGITS
     whom
    1.15
    whom
    1.07
     Whom
    0.98
    Whom
    0.96
     quien
    0.91
     hvem
    0.90
     who
    0.85
     whoſe
    0.82
    Who
    0.79
    who
    0.79
    Activations Density 0.296%

    No Known Activations