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

    Neuronpedia

    APICircuit 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. 18-GEMMASCOPE-RES-16K
    6. 10275
    Prev
    Next
    INDEX
    Explanations

    references to scientific articles and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corners
    -0.57
     Corners
    -0.48
    åg
    -0.47
     деле
    -0.47
     active
    -0.45
     Grade
    -0.45
     corner
    -0.44
    Corners
    -0.42
     Jep
    -0.42
     насељу
    -0.41
    POSITIVE LOGITS
     []:
    0.77
    StructEnd
    0.74
     nahilalakip
    0.73
     BrowserModule
    0.71
    AutoModerator
    0.69
    GenerationType
    0.69
    DeleteBehavior
    0.64
    ViewFeatures
    0.64
    __()
    0.64
     jScrollPane
    0.64
    Activations Density 0.356%

    No Known Activations