© 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. 10-GEMMASCOPE-RES-16K
    6. 11089
    Prev
    Next
    INDEX
    Explanations

    specific terms and references related to research studies and their components

    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
     lenker
    -0.64
     <=",
    -0.62
     esimer
    -0.58
    こうした
    -0.58
     piccole
    -0.57
     demais
    -0.56
     slowest
    -0.56
     tärke
    -0.56
    ďaka
    -0.56
     piccoli
    -0.55
    POSITIVE LOGITS
    TintMode
    0.88
    XmlAccessType
    0.82
    AnchorStyles
    0.63
    SharedCtor
    0.62
    tagHelperRunner
    0.59
    setLayoutManager
    0.57
    nictwa
    0.56
    adaptiveStyles
    0.56
    ollectionView
    0.54
    henswürdigkeiten
    0.54
    Activations Density 0.652%

    No Known Activations