© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 411
    Prev
    Next
    INDEX
    Explanations

    phrases indicating diversity and representation in characters or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.89
     autorytatywna
    -0.82
     <<<<<<<<<<<<<<
    -0.70
     للاسماء
    -0.67
     raiſ
    -0.63
    bmatrix
    -0.62
     مشين
    -0.62
    windowFixed
    -0.61
    ochet
    -0.60
    patent
    -0.59
    POSITIVE LOGITS
    AccessorTable
    0.55
     stabilité
    0.52
     précédentes
    0.50
    InteropServices
    0.46
     referenties
    0.46
    非
    0.46
     registros
    0.45
    genomen
    0.45
     suivants
    0.43
     racines
    0.43
    Activations Density 0.855%

    No Known Activations