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. 5-GEMMASCOPE-RES-16K
    6. 5532
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or syntactical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -1.07
     Мексичка
    -0.89
     AssemblyVersion
    -0.87
    CppMethod
    -0.84
    IndentedString
    -0.82
    Jeografia
    -0.82
    localctx
    -0.79
     Paglinawan
    -0.78
     архивлан
    -0.78
    Cyfeiriadau
    -0.77
    POSITIVE LOGITS
    </tr>
    0.64
     chré
    0.60
     nemici
    0.60
    0.60
    
    0.56
     chrétiens
    0.55
     eivät
    0.53
    ↵↵
    0.53
     gehad
    0.53
    talt
    0.52
    Activations Density 0.010%

    No Known Activations