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. 2160
    Prev
    Next
    INDEX
    Explanations

    information related to the development and characterization of biological or genetic processes and traits

    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
     Normdatei
    -0.83
    fjspx
    -0.82
     nakalista
    -0.82
    kuuta
    -0.72
    Lähteet
    -0.71
     للاسماء
    -0.71
    HtmlAttribute
    -0.66
    FormTagHelper
    -0.66
     &___
    -0.65
    ctuaries
    -0.65
    POSITIVE LOGITS
     generated
    1.68
     produced
    1.56
     arising
    1.28
     obtained
    1.25
     Produced
    1.22
    produced
    1.22
     created
    1.19
    generated
    1.18
    Produced
    1.15
     derived
    1.15
    Activations Density 1.389%

    No Known Activations