Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2157
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to chemical processes and data representation

    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
    SharedDtor
    -0.63
    msgSender
    -0.51
    ActionCreators
    -0.50
     sa
    -0.48
     har
    -0.47
    <h2>
    -0.47
     personal
    -0.46
    stereotype
    -0.44
     
    -0.44
     po
    -0.44
    POSITIVE LOGITS
    tvguidetime
    0.87
     itſelf
    0.83
     pleaſure
    0.73
    "]];
    0.73
    IUrlHelper
    0.72
    amaño
    0.71
    MemoryWarning
    0.71
    neſs
    0.70
    >\<^
    0.70
    findpost
    0.70
    Activations Density 6.104%

    No Known Activations