© 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. 16-GEMMASCOPE-RES-16K
    11. 10263
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <caption>
    -0.35
     británico
    -0.35
     fieltro
    -0.35
     parís
    -0.34
     scienza
    -0.34
    zbęd
    -0.33
     mármol
    -0.33
     hormigón
    -0.33
     compleja
    -0.32
     detalla
    -0.32
    POSITIVE LOGITS
     direction
    1.43
     DIRECTION
    1.26
     Direction
    1.26
    direction
    1.21
    Direction
    1.20
     directions
    1.16
     Directions
    1.10
     Richtung
    1.06
    DIRECTION
    1.03
     DIRECTIONS
    1.00
    Activations Density 0.212%

    No Known Activations