© 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. 2-GEMMASCOPE-RES-16K
    11. 14916
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "TODO" indicating tasks or actions that need to be completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Murat
    -0.69
    SourceChecksum
    -0.64
     Pizarro
    -0.60
    UnsafeEnabled
    -0.60
    佣
    -0.58
     Wiz
    -0.57
     lungs
    -0.57
     Visconti
    -0.54
     foot
    -0.53
    foot
    -0.53
    POSITIVE LOGITS
     dare
    0.95
     TODO
    0.92
    帖最后由
    0.77
     dares
    0.76
    DAOImpl
    0.72
    PhysRevD
    0.72
     emphasised
    0.71
     emphasise
    0.70
    makeConstraints
    0.70
     CURIAM
    0.70
    Activations Density 0.044%

    No Known Activations