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. 4-GEMMASCOPE-RES-16K
    6. 15835
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or parameters related to class definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getWriter
    -0.52
    牧
    -0.52
    émoc
    -0.50
    ↵↵
    -0.50
    detectChanges
    -0.48
     FileReader
    -0.48
     CMY
    -0.47
    ↵
    -0.47
    ix
    -0.46
    y
    -0.45
    POSITIVE LOGITS
     autorytatywna
    1.28
    Viitteet
    0.86
     localObject
    0.80
    sizeCache
    0.80
    MessageOf
    0.77
    Portale
    0.72
     հղումներ
    0.70
    homonymie
    0.70
     surla
    0.70
    ]._
    0.69
    Activations Density 0.072%

    No Known Activations