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. 12746
    Prev
    Next
    INDEX
    Explanations

    references to political criticism and accountability

    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
     bicchiere
    -0.55
     cucchia
    -0.55
     migli
    -0.53
     felicità
    -0.51
     cappuccio
    -0.49
     Physically
    -0.49
    !")
    
    -0.47
     piedi
    -0.47
     universel
    -0.47
     beginnetje
    -0.47
    POSITIVE LOGITS
    LookAnd
    0.83
    providedIn
    0.78
    NameInMap
    0.74
     political
    0.70
     betweenstory
    0.69
    ANDUM
    0.67
     Audiodateien
    0.67
    帖最后由
    0.66
    QMetaType
    0.64
    WithIOException
    0.64
    Activations Density 0.730%

    No Known Activations