Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 2796
    Prev
    Next
    INDEX
    Explanations

    assertions and cautions regarding political or social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     volont
    -0.48
    ?
    -0.46
    umph
    -0.43
     eller
    -0.43
     laiton
    -0.42
     принято
    -0.42
     spéciales
    -0.42
     Aufs
    -0.42
     ellos
    -0.42
     declarado
    -0.40
    POSITIVE LOGITS
    Personendaten
    1.05
    ValueStyle
    0.93
    NUMX
    0.86
    awtextra
    0.86
     autorytatywna
    0.85
     مشين
    0.84
    SharedDtor
    0.83
    存于互联网档案馆
    0.83
     nahilalakip
    0.78
    Chham
    0.78
    Activations Density 0.444%

    No Known Activations