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. 2-GEMMASCOPE-RES-16K
    6. 6162
    Prev
    Next
    INDEX
    Explanations

    references to input and output streams in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.71
     насељу
    -0.49
    onade
    -0.40
    omethane
    -0.39
    forChild
    -0.38
    vember
    -0.37
    MEMORANDUM
    -0.37
    щі
    -0.37
    Зноскі
    -0.36
    Referensi
    -0.36
    POSITIVE LOGITS
    io
    2.10
    IO
    1.91
    ios
    1.59
    IOS
    1.25
    ioo
    1.24
    ioa
    1.17
     IO
    1.15
    iole
    1.14
    iose
    1.08
    Io
    1.07
    Activations Density 2.096%

    No Known Activations