© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5942
    Prev
    Next
    INDEX
    Explanations

    references to specific protocols or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (@
    -0.39
    }{*}{}
    -0.35
     trekken
    -0.34
     Numerade
    -0.33
     base
    -0.33
     оригіналу
    -0.32
    SharedDtor
    -0.32
    السكان
    -0.32
     (_,
    -0.32
    stdafx
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.57
    Vidite
    0.57
    ViewFeatures
    0.56
    mybatisplus
    0.56
    Datuak
    0.52
     AssemblyVersion
    0.51
    yntaxException
    0.51
    MessageTagHelper
    0.50
    GEBURTS
    0.50
    uxxxx
    0.50
    Activations Density 2.228%

    No Known Activations