© 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. 3-GEMMASCOPE-RES-16K
    11. 10393
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing collective action or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     døde
    -0.64
     OBITUARY
    -0.60
    WireFormatLite
    -0.58
     Arro
    -0.57
    TypeMap
    -0.56
     palvel
    -0.54
    onor
    -0.53
     ')[
    -0.52
    Alter
    -0.51
    batore
    -0.51
    POSITIVE LOGITS
    Lets
    1.49
     lets
    1.38
     Lets
    1.38
    Давайте
    0.97
    lets
    0.94
     let
    0.91
     Let
    0.91
    Vamos
    0.85
    让我们
    0.84
    Let
    0.82
    Activations Density 0.066%

    No Known Activations