© 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. 2-GEMMASCOPE-RES-16K
    11. 2128
    Prev
    Next
    INDEX
    Explanations

    instances of the word "faced" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.52
    MigrationBuilder
    -0.46
    ufnahme
    -0.40
    OOTDTY
    -0.39
     ब्रेकडाउन
    -0.38
    UnusedPrivate
    -0.36
    مكان
    -0.35
     ***!
    -0.35
    peicher
    -0.35
     đôi
    -0.34
    POSITIVE LOGITS
     faced
    1.15
    faced
    0.91
     Direction
    0.91
     Faced
    0.90
    Direction
    0.88
     direction
    0.87
    facing
    0.82
     facing
    0.80
    direction
    0.79
     Facing
    0.78
    Activations Density 0.143%

    No Known Activations