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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 7389
    Prev
    Next
    INDEX
    Explanations

    numeric data and structural elements, especially related to scientific and computational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovac
    -0.50
    örk
    -0.48
     تضيفلها
    -0.47
    φα
    -0.46
    Jîn
    -0.46
     isInitialized
    -0.45
    relativeTime
    -0.45
    rxjs
    -0.44
     Winaray
    -0.44
    uminescence
    -0.44
    POSITIVE LOGITS
    RetentionPolicy
    0.58
    ménage
    0.57
    Geografie
    0.55
    spatial
    0.55
     useStyles
    0.54
    liosis
    0.54
    BagConstraints
    0.53
    sidemargin
    0.53
    ندية
    0.53
    Enllaces
    0.53
    Activations Density 5.933%

    No Known Activations