© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 16099
    Prev
    Next
    INDEX
    Explanations

    numeric expressions and mathematical operations

    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
     asing
    -0.66
     oprot
    -0.61
     propOrder
    -0.61
    complexContent
    -0.57
     Drapeau
    -0.57
     relâche
    -0.56
    unikasi
    -0.56
     indisponible
    -0.55
     Kj
    -0.55
     Sew
    -0.55
    POSITIVE LOGITS
     Blatt
    0.78
    chengladbach
    0.73
     CUB
    0.70
     Alderman
    0.69
     Alder
    0.69
    SpringBootTest
    0.67
    Alder
    0.67
     Arden
    0.67
     Blätter
    0.66
     Dexter
    0.64
    Activations Density 2.264%

    No Known Activations