© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7121
    Prev
    Next
    INDEX
    Explanations

    the repeated use of the word "ve" indicating a focus on personal experiences or reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.63
    ᅠ
    -0.56
    Investments
    -0.54
     ModelExpression
    -0.54
     Robots
    -0.53
     Folders
    -0.52
     Planets
    -0.50
     wars
    -0.50
     Crusoe
    -0.50
     Vel
    -0.50
    POSITIVE LOGITS
    ive
    1.00
    ve
    0.90
    IVE
    0.88
    VE
    0.76
    Ive
    0.66
     ive
    0.65
    ives
    0.58
     Ive
    0.53
    Ve
    0.51
    ove
    0.50
    Activations Density 0.244%

    No Known Activations