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. 11032
    Prev
    Next
    INDEX
    Explanations

    the beginning of a document or a distinct section within a text

    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
    e
    -1.01
    ed
    -0.91
     tanks
    -0.80
     tank
    -0.78
     Lons
    -0.78
    нке
    -0.76
    2
    -0.75
     Tank
    -0.74
     Aufs
    -0.74
    onde
    -0.73
    POSITIVE LOGITS
    __':
    
    1.46
    ()))
    
    1.42
    __":
    
    1.36
    ]))
    
    1.35
    ']))
    
    1.34
    '))
    
    1.29
    }")
    
    1.29
    })();
    
    1.28
    }));
    
    1.26
    '])){
    
    1.25
    Activations Density 0.054%

    No Known Activations