Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4016
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses in a document

    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
    MessageOf
    -0.68
     Meksiku
    -0.58
     ModelExpression
    -0.54
    localctx
    -0.52
     trans
    -0.50
    richTextPanel
    -0.49
    setVerticalGroup
    -0.47
    款
    -0.46
     مواليد
    -0.46
    itamos
    -0.46
    POSITIVE LOGITS
     tartalomajánló
    0.67
     Miscell
    0.66
    ChildIndex
    0.64
     betweenstory
    0.62
    ειτουργ
    0.61
    InitVars
    0.60
     myſelf
    0.60
    OCKET
    0.59
     Chriftian
    0.59
    !("{
    0.58
    Activations Density 0.042%

    No Known Activations