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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 8013
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce examples or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Económica
    -0.57
    ⋱
    -0.55
    ")]
    
    -0.51
     Constitucional
    -0.49
    "));
    
    -0.47
     transfé
    -0.47
    '));
    
    -0.47
    "]];
    -0.45
     "/")
    -0.45
     vito
    -0.44
    POSITIVE LOGITS
     such
    1.06
     såsom
    0.92
    such
    0.89
     tels
    0.87
     takich
    0.85
     AssemblyProduct
    0.85
     telles
    0.85
     zoals
    0.83
    itemBuilder
    0.82
     kuten
    0.81
    Activations Density 0.192%

    No Known Activations