© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 14960
    Prev
    Next
    INDEX
    Explanations

    references to filenames in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    -0.66
     cent
    -0.62
     Co
    -0.60
    k
    -0.60
     k
    -0.58
    ter
    -0.56
     K
    -0.56
     Pa
    -0.55
    id
    -0.55
     co
    -0.55
    POSITIVE LOGITS
     filename
    1.67
    filename
    1.60
     filenames
    1.41
     Filename
    1.41
     FileName
    1.36
    FILENAME
    1.30
    FileName
    1.27
    Filename
    1.25
    filenames
    1.25
    文件名
    1.20
    Activations Density 0.063%

    No Known Activations