© 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. 40-GEMMASCOPE-RES-16K
    11. 7765
    Prev
    Next
    INDEX
    Explanations

    key events, transitions, and significant outcomes in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    发表于
    -0.44
     Autorisations
    -0.43
     resourceCulture
    -0.41
    Есть
    -0.40
     יש
    -0.40
     Есть
    -0.39
     якщо
    -0.38
    媲
    -0.38
     fometimes
    -0.38
     אנחנו
    -0.37
    POSITIVE LOGITS
     realizing
    1.20
     realising
    1.12
     fearing
    1.12
    Unable
    1.05
     feeling
    1.05
     sensing
    1.04
    Feeling
    1.02
     convinced
    1.01
     believing
    1.00
     Feeling
    1.00
    Activations Density 0.566%

    No Known Activations