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. 6846
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands for beginning a new environment or section

    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
    "])
    
    -0.86
    ']))
    
    -0.81
    )}</
    -0.79
    ]++;
    -0.79
    '])
    
    -0.79
    thâu
    -0.74
    ')")
    -0.74
    ")));
    
    -0.72
    ]--;
    -0.72
    ++
    
    -0.70
    POSITIVE LOGITS
     beginners
    1.80
     beginner
    1.72
     Beginners
    1.70
    Begin
    1.60
    Beginner
    1.56
     Beginner
    1.49
    begin
    1.40
     Anfänger
    1.39
     novice
    1.32
     novices
    1.23
    Activations Density 0.096%

    No Known Activations