© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8581
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce authors or creators of content

    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
    Ārējās
    -0.76
     Préférences
    -0.68
     ditemp
    -0.67
     démocr
    -0.66
    Datuak
    -0.65
     normaux
    -0.64
     suivants
    -0.64
     placée
    -0.64
    SequentialGroup
    -0.64
     overras
    -0.64
    POSITIVE LOGITS
     about
    0.60
    permitAll
    0.51
     kuhusu
    0.51
     concerning
    0.51
     ABOUT
    0.50
     despre
    0.49
    bout
    0.48
     apie
    0.47
     About
    0.47
     Sobre
    0.47
    Activations Density 0.077%

    No Known Activations