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. 5-GEMMASCOPE-RES-16K
    6. 1586
    Prev
    Next
    INDEX
    Explanations

    terms related to official documentation and identification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.69
    ScopeManager
    -0.56
    !*\
    -0.54
    ConstraintMaker
    -0.52
    ंदीखरीदारी
    -0.50
     even
    -0.50
    minecraftforge
    -0.50
    DockStyle
    -0.48
     OGSÅ
    -0.47
    therin
    -0.47
    POSITIVE LOGITS
    MarshalTo
    0.61
    NOPQRST
    0.58
    epiece
    0.57
     copies
    0.56
    zeug
    0.56
    Gat
    0.54
    saraba
    0.54
     attested
    0.53
     pickles
    0.53
     phúc
    0.53
    Activations Density 0.216%

    No Known Activations