© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 816
    Prev
    Next
    INDEX
    Explanations

    phrases related to direction and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Args
    -0.40
    awan
    -0.38
     pozn
    -0.38
     Raised
    -0.37
    нибудь
    -0.37
    źni
    -0.36
     оригіналу
    -0.36
    veen
    -0.36
    Raised
    -0.36
    ạm
    -0.34
    POSITIVE LOGITS
     direction
    3.01
     Direction
    2.62
     directions
    2.59
    direction
    2.51
     DIRECTION
    2.43
    Direction
    2.34
    directions
    2.21
     Directions
    2.16
    DIRECTION
    2.04
    方向
    2.02
    Activations Density 0.340%

    No Known Activations