© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 10397
    Prev
    Next
    INDEX
    Explanations

    procedural and methodological details in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.53
    PerformLayout
    -0.42
     BoxDecoration
    -0.41
     Préférences
    -0.41
    OGND
    -0.40
    QPalette
    -0.38
    enumii
    -0.38
     arşivlendi
    -0.37
     ***!
    -0.36
     ChromeDriver
    -0.36
    POSITIVE LOGITS
     duration
    1.28
     durations
    1.17
     prolonged
    1.12
    duration
    1.09
     Duration
    1.07
     lasted
    1.06
    Duration
    1.05
     duración
    1.04
     longer
    1.02
     longest
    0.98
    Activations Density 0.648%

    No Known Activations