© 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. 5-GEMMASCOPE-RES-16K
    6. 445
    Prev
    Next
    INDEX
    Explanations

    expressions related to significant actions or events involving "it"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bort
    -0.44
     carreras
    -0.43
     rostros
    -0.43
     regiones
    -0.43
     sentada
    -0.43
     muestras
    -0.43
     prés
    -0.43
     ciudades
    -0.42
     regioni
    -0.41
     estacionamiento
    -0.41
    POSITIVE LOGITS
    oneofs
    0.80
     tartalomajánló
    0.77
    Chham
    0.74
     kaarangay
    0.70
     houſe
    0.70
    навли
    0.69
     Majefty
    0.68
    sprzedam
    0.67
     thrills
    0.66
     chills
    0.66
    Activations Density 0.363%

    No Known Activations