© 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. 23-GEMMASCOPE-RES-16K
    6. 14648
    Prev
    Next
    INDEX
    Explanations

    code snippets related to multimedia asset handling and manipulation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.92
    EndGlobalSection
    -0.91
    CloseOperation
    -0.83
     AssemblyTitle
    -0.81
     propOrder
    -0.78
    __(/*!
    -0.76
    GEBURTSDATUM
    -0.76
    Geplaatst
    -0.75
    IVEREF
    -0.74
    complexContent
    -0.73
    POSITIVE LOGITS
    init
    0.63
     init
    0.43
     Weiner
    0.43
     system
    0.42
     almost
    0.41
     From
    0.40
    axel
    0.39
    From
    0.39
     Cartwright
    0.39
    ノ
    0.39
    Activations Density 0.248%

    No Known Activations