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. 1563
    Prev
    Next
    INDEX
    Explanations

    elements related to CSS properties and styles

    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
    Portail
    -0.91
     незавершена
    -0.89
    __((
    -0.82
    setVerticalGroup
    -0.77
    OGND
    -0.76
    ThroughAttribute
    -0.76
    存于互联网档案馆
    -0.74
    
    -0.73
    PropertyChanging
    -0.70
    sizeCache
    -0.70
    POSITIVE LOGITS
    crombie
    0.60
    quip
    0.52
    glie
    0.52
     Contempor
    0.45
    ECE
    0.45
     getById
    0.44
    ukin
    0.44
    ····
    0.44
    busch
    0.43
    esac
    0.43
    Activations Density 0.125%

    No Known Activations