© 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. 2-GEMMASCOPE-RES-16K
    6. 8873
    Prev
    Next
    INDEX
    Explanations

    references to method calls or functions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.93
     disambiguazione
    -0.78
     للمعارف
    -0.75
    sizeCache
    -0.75
     Geſ
    -0.75
    fromnode
    -0.74
     queſta
    -0.72
     erſt
    -0.71
     lenker
    -0.70
    -------
    -0.69
    POSITIVE LOGITS
    readonly
    0.40
    @
    0.38
    ////////////////
    0.33
     istore
    0.30
    pertory
    0.28
     Along
    0.28
    少
    0.28
     jäl
    0.28
    IList
    0.27
    findpost
    0.27
    Activations Density 0.107%

    No Known Activations