© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5858
    Prev
    Next
    INDEX
    Explanations

    technical jargon and keywords related to programming and data structures

    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
    GEBURTSDATUM
    -0.59
    Tikang
    -0.55
    RectangleBorder
    -0.54
     Roskov
    -0.51
     pinulongan
    -0.51
     myſelf
    -0.49
    出版年
    -0.48
     Photocase
    -0.48
     itſelf
    -0.47
     betweenstory
    -0.46
    POSITIVE LOGITS
    requireNonNull
    0.44
     aload
    0.43
    InitStructure
    0.42
     isNameExpr
    0.39
    onViewCreated
    0.38
     iVar
    0.38
    hikariConfig
    0.37
     ίδ
    0.37
     requête
    0.36
    Herkunft
    0.36
    Activations Density 0.237%

    No Known Activations