© 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. 38-GEMMASCOPE-RES-16K
    11. 12954
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to direction and positional changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Right
    -1.01
    右側
    -1.00
     右
    -0.96
    右侧
    -0.96
    RIGHT
    -0.94
    右边
    -0.93
     Right
    -0.91
    右
    -0.83
    右手
    -0.81
     RIGHT
    -0.79
    POSITIVE LOGITS
     left
    0.77
     le
    0.74
     lett
    0.56
     LE
    0.53
    left
    0.49
     ле
    0.48
     leave
    0.45
     lasciato
    0.45
     eft
    0.44
     igjen
    0.39
    Activations Density 0.301%

    No Known Activations