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. 14592
    Prev
    Next
    INDEX
    Explanations

    PHP code syntax elements related to variable assignments and function parameters

    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
    tvguidetime
    -0.87
    XmlType
    -0.71
     كره
    -0.67
    GEBURTSDATUM
    -0.67
    AnimationsModule
    -0.65
    ">—
    -0.63
    Искәрмәләр
    -0.63
    Webster
    -0.62
    სქოლიო
    -0.61
    sptr
    -0.60
    POSITIVE LOGITS
    AndroidJUnit
    0.95
    AnchorStyles
    0.67
     Überras
    0.60
     dibujos
    0.60
    تفصیلات
    0.54
     hout
    0.54
     Cual
    0.53
     desenhos
    0.53
     Dah
    0.52
     herself
    0.52
    Activations Density 0.038%

    No Known Activations