Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 3071
    Prev
    Next
    INDEX
    Explanations

    file paths and command-line options related to software installation and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.51
    ">)</
    -0.47
     assurent
    -0.46
     pendek
    -0.44
    }],
    
    -0.41
    CloseOperation
    -0.40
    fileID
    -0.39
     Aufla
    -0.39
     cappuccio
    -0.39
     habis
    -0.39
    POSITIVE LOGITS
    sizeCache
    0.82
     "..\..\..\
    0.81
    MessageOf
    0.80
    rrggbb
    0.78
    OGND
    0.75
    :✨
    0.73
    Portale
    0.73
    MigrationBuilder
    0.69
    expandindo
    0.67
    Хьажоргаш
    0.65
    Activations Density 0.381%

    No Known Activations