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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14449
    Prev
    Next
    INDEX
    Explanations

    structured data definitions and programming constructs

    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
    openqa
    -0.36
     Pingback
    -0.35
     kalian
    -0.35
    AndEndTag
    -0.34
     presentarse
    -0.33
     ligiloj
    -0.33
     tambi
    -0.32
     levure
    -0.31
     redacción
    -0.30
    getRuntime
    -0.30
    POSITIVE LOGITS
     _
    1.90
     (_
    1.42
    ._
    1.40
     "_
    1.39
    (_
    1.37
     '_
    1.37
    =_
    1.29
    ,_
    1.28
    :_
    1.26
     {_
    1.26
    Activations Density 1.476%

    No Known Activations