© 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. 21-GEMMASCOPE-RES-16K
    11. 2197
    Prev
    Next
    INDEX
    Explanations

    references to legal frameworks and concepts within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.84
    ,:);
    -0.81
    multer
    -0.75
    AsUp
    -0.75
    StackNavigator
    -0.73
     EClass
    -0.73
     InputDecoration
    -0.72
     Italijani
    -0.71
    ImageField
    -0.70
    PARATOR
    -0.70
    POSITIVE LOGITS
     thereby
    0.70
     which
    0.64
     بتوان
    0.61
     to
    0.56
     уж
    0.55
     daarbij
    0.55
     sirva
    0.55
     ayude
    0.55
     possam
    0.54
     permita
    0.54
    Activations Density 0.420%

    No Known Activations