© 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. 7511
    Prev
    Next
    INDEX
    Explanations

    actions and events related to initiation and completion 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
    脚注の使い方
    -0.50
     Normdatei
    -0.47
    queryInterface
    -0.44
     devrez
    -0.42
    Datuak
    -0.40
     verrez
    -0.39
    RTLU
    -0.38
     propOrder
    -0.37
     devriez
    -0.37
     урна
    -0.36
    POSITIVE LOGITS
     off
    3.92
    off
    3.00
     Off
    2.97
    Off
    2.95
     OFF
    2.63
    OFF
    2.39
    オフ
    2.13
    offs
    2.05
     offs
    1.91
     オフ
    1.73
    Activations Density 0.645%

    No Known Activations