© 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. 3-GEMMASCOPE-RES-16K
    6. 10725
    Prev
    Next
    INDEX
    Explanations

    instances of different types of JSON readers and writers used in data serialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Knockout
    -0.56
     Theſe
    -0.56
    abank
    -0.55
     noDo
    -0.53
    koń
    -0.51
     coag
    -0.50
    ξι
    -0.50
    Knock
    -0.49
    InstanceOf
    -0.49
     Seitz
    -0.49
    POSITIVE LOGITS
    Reader
    2.56
     Reader
    1.96
    reader
    1.81
    Writer
    1.61
     READER
    1.38
     reader
    1.36
    FileReader
    1.18
    StreamReader
    1.16
     FileReader
    1.16
    eader
    1.15
    Activations Density 0.060%

    No Known Activations