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. 6-GEMMASCOPE-RES-16K
    6. 13543
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and syntax elements in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bene
    -0.52
     Tek
    -0.50
    benen
    -0.48
    Dati
    -0.46
     tek
    -0.45
     HTT
    -0.44
    ilhas
    -0.44
    ليق
    -0.44
     tecn
    -0.44
    buttonBar
    -0.43
    POSITIVE LOGITS
     (!__
    1.38
     '__
    1.32
     EconPapers
    0.93
     "__
    0.92
     &___
    0.92
    (!__
    0.91
    ).__
    0.91
    ().__
    0.89
    +:+
    0.88
     utafitiHapana
    0.83
    Activations Density 0.038%

    No Known Activations