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. 1-GEMMASCOPE-RES-16K
    6. 6167
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.91
     Wikimedijinoj
    -0.82
    )");
    
    -0.81
    GEBURTSDATUM
    -0.79
    )";
    
    -0.79
    elemField
    -0.78
     beginnetje
    -0.77
    ]';
    -0.76
     Référence
    -0.76
     NgModule
    -0.75
    POSITIVE LOGITS
    leştir
    0.55
    icksburg
    0.43
    portál
    0.42
     همچنین
    0.41
     pertanto
    0.41
    精力
    0.41
     combinatie
    0.40
    Sprintf
    0.39
    私が
    0.39
     ayrıca
    0.38
    Activations Density 0.159%

    No Known Activations