© 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. 34-GEMMASCOPE-RES-16K
    11. 13261
    Prev
    Next
    INDEX
    Explanations

    concepts related to data processing and analysis, particularly smooth transitions 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 @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.45
     INTERESAR
    -0.39
     Schuyler
    -0.32
    tzmann
    -0.32
    didSet
    -0.31
     gefe
    -0.31
     propOrder
    -0.30
    ünf
    -0.29
    sept
    -0.29
    ншот
    -0.29
    POSITIVE LOGITS
     smooth
    3.08
     Smooth
    2.78
    smooth
    2.75
    Smooth
    2.69
     smoothness
    2.59
     smoother
    2.58
     smoothly
    2.28
     SMO
    2.16
     smoothed
    2.14
     smoothing
    2.06
    Activations Density 0.422%

    No Known Activations