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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15154
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical operations and symbols

    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
    
    -0.52
     szóci
    -0.50
    боро
    -0.47
     tangga
    -0.44
    UnusedPrivate
    -0.43
     vectorielles
    -0.42
     Int
    -0.42
     curiosidad
    -0.42
    ภัย
    -0.42
     científicas
    -0.42
    POSITIVE LOGITS
    
    0.82
     endregion
    0.77
    SourceChecksum
    0.76
    KURZBESCHREIBUNG
    0.73
    +:+
    0.71
    Tikang
    0.70
    脚注の使い方
    0.66
     Viber
    0.66
     Anſ
    0.63
    ScopeManager
    0.63
    Activations Density 0.190%

    No Known Activations