© 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. 15-GEMMASCOPE-RES-16K
    6. 8872
    Prev
    Next
    INDEX
    Explanations

    occurrences of quoting or referencing in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ali
    -0.49
     Ali
    -0.47
    <eos>
    -0.45
     U
    -0.44
    ijs
    -0.43
    nlm
    -0.42
    aspx
    -0.41
    auta
    -0.40
    anza
    -0.40
     gr
    -0.40
    POSITIVE LOGITS
     esternos
    0.84
    UnusedPrivate
    0.83
     africain
    0.82
    setupUi
    0.80
    StoryboardSegue
    0.79
     africaine
    0.75
     saites
    0.72
    Климат
    0.72
    Lähteet
    0.71
     initComponents
    0.70
    Activations Density 0.031%

    No Known Activations