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. 23-GEMMASCOPE-RES-16K
    6. 5830
    Prev
    Next
    INDEX
    Explanations

    references to eCommerce platforms and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rlpool
    -0.58
     hindurch
    -0.51
     pagină
    -0.49
     semula
    -0.49
     libur
    -0.49
    
    -0.49
    Erreferentziak
    -0.48
     schermata
    -0.48
    DataContract
    -0.48
     tuong
    -0.47
    POSITIVE LOGITS
     consistency
    1.20
     accuracy
    1.19
     affordability
    1.19
     reliability
    1.19
     cleanliness
    1.17
     practicality
    1.17
     durability
    1.16
     flexibility
    1.12
     efficiency
    1.11
     simplicity
    1.11
    Activations Density 0.642%

    No Known Activations