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. 19-GEMMASCOPE-RES-16K
    6. 11115
    Prev
    Next
    INDEX
    Explanations

    references to the history and status of a product or service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.69
    kloped
    -0.67
     jScrollPane
    -0.65
    whelmed
    -0.64
    WriteBarrier
    -0.63
     متحده
    -0.62
    vinced
    -0.61
    ChromeDriver
    -0.60
    LLocation
    -0.60
    jestel
    -0.59
    POSITIVE LOGITS
     available
    0.76
     being
    0.63
     sold
    0.57
     ready
    0.57
     marketed
    0.57
     destined
    0.56
     undergoing
    0.56
     shipped
    0.56
     subject
    0.52
     priced
    0.51
    Activations Density 0.648%

    No Known Activations