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. 13-GEMMASCOPE-RES-16K
    6. 12394
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to features or feature selection in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PVA
    -0.93
     pessoais
    -0.90
     BorderRadius
    -0.87
    ILON
    -0.87
    Alp
    -0.86
     ALP
    -0.86
     kantoor
    -0.84
     LDA
    -0.83
    idp
    -0.82
     intoxication
    -0.81
    POSITIVE LOGITS
     features
    1.96
     feature
    1.77
     Features
    1.67
    Features
    1.60
    features
    1.60
     FEATURE
    1.57
     Feature
    1.52
     FEATURES
    1.46
    Feature
    1.44
    feature
    1.42
    Activations Density 0.048%

    No Known Activations