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. 13-GEMMASCOPE-RES-16K
    6. 9406
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts that indicate groups, connections, or relationships among entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.89
     itſelf
    -0.87
    MLLoader
    -0.85
     ſeveral
    -0.82
    Personendaten
    -0.82
    InputBorder
    -0.81
    arraycopy
    -0.79
     myſelf
    -0.78
     Efq
    -0.78
    drawal
    -0.78
    POSITIVE LOGITS
    putan
    0.47
     this
    0.46
     including
    0.44
    this
    0.44
    שם
    0.43
     okolí
    0.42
    il
    0.40
     tarifas
    0.40
    Mantenimiento
    0.40
    Initializable
    0.40
    Activations Density 0.741%

    No Known Activations