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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 4951
    Prev
    Next
    INDEX
    Explanations

    special characters, particularly underscores and hyphens in code or script contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yana
    -0.56
     cytoplasm
    -0.51
     trasparente
    -0.50
     spirituale
    -0.50
     applicazioni
    -0.50
     choisis
    -0.49
     fondateur
    -0.49
     scolaires
    -0.49
     quæ
    -0.48
     suivants
    -0.48
    POSITIVE LOGITS
     للمعارف
    0.94
     дописавши
    0.89
     <>",
    0.87
    EDEFAULT
    0.86
     незавершена
    0.86
     autorytatywna
    0.85
    Personendaten
    0.84
    TypedDataSet
    0.84
    ValueStyle
    0.83
    #+#
    0.82
    Activations Density 0.501%

    No Known Activations