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. 10-GEMMASCOPE-RES-16K
    6. 12920
    Prev
    Next
    INDEX
    Explanations

    code snippets related to file input/output operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -1.18
     Anſ
    -1.05
     itſelf
    -1.03
     Shakspeare
    -0.99
     themſelves
    -0.98
     pleaſure
    -0.98
     myſelf
    -0.97
     fevere
    -0.96
    aarrggbb
    -0.94
     raiſ
    -0.93
    POSITIVE LOGITS
     file
    0.93
     File
    0.88
    File
    0.82
    file
    0.79
    AccessFile
    0.70
     files
    0.70
     FILE
    0.68
    FILE
    0.65
    fstream
    0.61
    isfile
    0.55
    Activations Density 0.263%

    No Known Activations