© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 6073
    Prev
    Next
    INDEX
    Explanations

    concepts related to cardiomyopathy and genetic factors influencing cell survival

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.88
     a
    -0.83
      
    -0.83
    <eos>
    -0.83
    .
    -0.83
    -
    -0.80
    S
    -0.75
     
    -0.73
    :
    -0.72
    ↵↵
    -0.72
    POSITIVE LOGITS
     يتيمه
    1.50
     незавершена
    1.43
     متعلقه
    1.41
     Мексичка
    1.39
     للمعارف
    1.38
     ſche
    1.31
     ſind
    1.31
    IntoConstraints
    1.29
    ſelf
    1.29
     ſever
    1.28
    Activations Density 1.520%

    No Known Activations