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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7692
    Prev
    Next
    INDEX
    Explanations

    terms related to leaks or leakage, particularly in various contexts

    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
    '))
    
    -0.83
     {}));
    -0.82
    دانشنامهٔ
    -0.79
    )))
    
    -0.78
    ())))
    -0.78
    _));
    -0.77
    rrggbb
    -0.76
     Walkover
    -0.75
    oredCriteria
    -0.72
    ]))
    
    -0.72
    POSITIVE LOGITS
     versus
    0.69
     verses
    0.66
    WEBPACK
    0.63
    【
    0.62
    versus
    0.61
     Versus
    0.58
     leaks
    0.58
    le
    0.56
     leaking
    0.54
     verse
    0.51
    Activations Density 0.114%

    No Known Activations