© 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. 10-GEMMASCOPE-RES-16K
    11. 15917
    Prev
    Next
    INDEX
    Explanations

    references to specific institutions and related entities

    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
    öglichkeiten
    -0.76
     GenerationType
    -0.75
    httphttps
    -0.74
    jest
    -0.69
    ThemeOverlay
    -0.69
    /*
    -0.67
     الحره
    -0.66
    Refrain
    -0.66
    userRepository
    -0.65
     Gerrard
    -0.65
    POSITIVE LOGITS
     Smo
    1.40
    Smo
    1.30
     SM
    1.21
    smo
    1.16
    sm
    1.16
    SM
    1.15
     smo
    1.14
    Sm
    1.13
     Sm
    1.11
     SMI
    1.09
    Activations Density 0.105%

    No Known Activations