© 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. 1-GEMMASCOPE-RES-16K
    11. 9857
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific phonetic patterns or sequences of letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    faßt
    -0.32
    trzyma
    -0.28
    RegistryLite
    -0.27
     grabado
    -0.27
     go
    -0.27
     quieran
    -0.26
     portátiles
    -0.26
     ಗ
    -0.26
     GO
    -0.25
     concentrado
    -0.25
    POSITIVE LOGITS
    gas
    1.51
    gs
    1.41
    ging
    1.41
    gam
    1.38
    gal
    1.38
    gie
    1.38
    gos
    1.37
    gers
    1.36
    gies
    1.34
    gon
    1.34
    Activations Density 0.450%

    No Known Activations