© 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. 2-GEMMASCOPE-RES-16K
    11. 6480
    Prev
    Next
    INDEX
    Explanations

    technical terms and measurements related to scientific experiments and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.91
    expandindo
    -0.82
     GenerationType
    -0.76
     betweenstory
    -0.73
    ActionCreators
    -0.72
     MonoBehaviour
    -0.71
     مرئيه
    -0.70
    DeleteBehavior
    -0.67
     onCreateView
    -0.67
    Portály
    -0.65
    POSITIVE LOGITS
    новременно
    0.75
     Baillargeon
    0.60
    illerato
    0.52
     dagegen
    0.50
     daß
    0.50
    })*/
    0.50
    adori
    0.50
    нодоро
    0.49
     Höhe
    0.49
     devant
    0.49
    Activations Density 7.663%

    No Known Activations