© 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. 36-GEMMASCOPE-RES-16K
    11. 12590
    Prev
    Next
    INDEX
    Explanations

    different perspectives or points of view presented in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المكان
    -0.42
    entuh
    -0.42
    ノベーション
    -0.41
    ukses
    -0.39
     Regel
    -0.37
    \{\\
    -0.37
    patent
    -0.37
    ampaikan
    -0.36
    不成
    -0.36
     ioutil
    -0.36
    POSITIVE LOGITS
     perspective
    2.89
     perspectives
    2.36
    perspective
    2.34
     Perspective
    2.23
     viewpoint
    2.16
    Perspective
    2.11
     perspectiva
    2.09
     PERSPECT
    2.08
     perspek
    2.03
     perspec
    1.91
    Activations Density 0.457%

    No Known Activations