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. 19-GEMMASCOPE-RES-16K
    6. 1977
    Prev
    Next
    INDEX
    Explanations

    information related to variables and how they change across different conditions or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ivelany
    -0.53
    зулта
    -0.51
     跳转至
    -0.48
     للمعارف
    -0.47
    })();
    
    -0.47
    疵
    -0.45
     lenker
    -0.44
    Arri
    -0.44
    Kjelder
    -0.43
     Rial
    -0.43
    POSITIVE LOGITS
     depend
    1.31
     depends
    1.29
     dependent
    1.28
     dependence
    1.25
     depended
    1.15
    depends
    1.14
     Dependence
    1.12
     dépend
    1.12
     depending
    1.10
     dependency
    1.08
    Activations Density 1.448%

    No Known Activations