© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7664
    Prev
    Next
    INDEX
    Explanations

    references to atmospheric conditions and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasBeenSet
    -0.65
    doGet
    -0.64
     Demp
    -0.60
    anthemum
    -0.59
    grunt
    -0.58
     Esprit
    -0.58
    Рей
    -0.57
     Gruy
    -0.56
    oneph
    -0.56
    GetMapping
    -0.56
    POSITIVE LOGITS
    enderror
    0.86
     onOptions
    0.75
    __(/*!
    0.74
     pitié
    0.74
    tvguidetime
    0.72
     Soro
    0.71
     afhankelijk
    0.69
     "..\..\..\
    0.69
     Berks
    0.66
    WebElementEntity
    0.66
    Activations Density 0.061%

    No Known Activations