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. 1-GEMMASCOPE-RES-16K
    6. 9591
    Prev
    Next
    INDEX
    Explanations

    terms related to ultraviolet (UV) radiation and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.62
    doms
    -0.59
    verwijspagina
    -0.56
    MigrationBuilder
    -0.53
     onCreateView
    -0.53
     spoke
    -0.53
     fieldNum
    -0.52
     Wikimedijinoj
    -0.52
    yny
    -0.51
    avits
    -0.51
    POSITIVE LOGITS
     radiation
    0.82
     Radiation
    0.72
    radiation
    0.70
    Radiation
    0.64
    ScopeManager
    0.62
     RADIATION
    0.60
    ase
    0.60
    AddTagHelper
    0.59
    ases
    0.58
    enderror
    0.58
    Activations Density 2.127%

    No Known Activations