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. 10-GEMMASCOPE-RES-16K
    6. 16355
    Prev
    Next
    INDEX
    Explanations

    geographical locations and state abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.86
     estekak
    -0.81
    %"),
    -0.79
    '));
    
    -0.79
    RectangleBorder
    -0.78
     ]
    
    -0.77
    '),
    
    -0.76
    ")));
    
    -0.75
     ")[
    -0.75
    }")
    
    -0.74
    POSITIVE LOGITS
    .,
    0.50
    시오
    0.49
    opcao
    0.47
     IndexPath
    0.47
    kuuta
    0.46
     שוליים
    0.46
     autora
    0.46
    Cal
    0.45
    所示
    0.45
    CAL
    0.45
    Activations Density 0.096%

    No Known Activations