© 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. 15-GEMMASCOPE-RES-16K
    11. 5392
    Prev
    Next
    INDEX
    Explanations

    concepts related to modularity and independence in structures, particularly in systems and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eliminación
    -0.40
     expansión
    -0.36
     evolución
    -0.35
     ocupación
    -0.34
     modified
    -0.33
    rolo
    -0.33
    consulté
    -0.32
     elimination
    -0.32
    久的
    -0.32
     ampliación
    -0.32
    POSITIVE LOGITS
     Separate
    0.87
     separate
    0.84
    separate
    0.82
     terpisah
    0.82
    Separate
    0.81
     seperate
    0.76
     separated
    0.74
     SEPAR
    0.74
     separ
    0.73
     sépar
    0.73
    Activations Density 1.201%

    No Known Activations