© 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. 2-GEMMASCOPE-RES-16K
    6. 8748
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical notation or expressions in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anyahu
    -0.65
    ArgsConstructor
    -0.59
    UMBIA
    -0.59
    ViewImports
    -0.59
    WithMany
    -0.59
    воря
    -0.58
     Kuan
    -0.58
     scu
    -0.57
     compacto
    -0.57
     compact
    -0.56
    POSITIVE LOGITS
    boldsymbol
    1.86
    Ess
    0.74
     snippetHide
    0.69
     elder
    0.68
    AppMethodBeat
    0.68
     Ess
    0.67
    }")
    
    0.65
     Elias
    0.65
    Elias
    0.65
     Grandmother
    0.65
    Activations Density 0.118%

    No Known Activations