© 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. 3-GEMMASCOPE-RES-16K
    11. 4312
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "front" and its contextual variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uellement
    -0.44
    ărul
    -0.40
     otomatig
    -0.40
     Lute
    -0.39
    kwds
    -0.39
    /*
    -0.38
     للمعارف
    -0.37
     Préférences
    -0.37
    mazoo
    -0.36
     SQLAlchemy
    -0.36
    POSITIVE LOGITS
     front
    4.41
    Front
    3.86
    front
    3.84
     Front
    3.83
     FRONT
    3.55
    FRONT
    3.34
     fronts
    3.05
     frontend
    2.52
    fron
    2.45
    フロント
    2.45
    Activations Density 0.070%

    No Known Activations