© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2673
    Prev
    Next
    INDEX
    Explanations

    mentions of personal relationships and family details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ))))
    -0.50
     innovate
    -0.49
    ])))
    -0.47
     Innovation
    -0.46
     innovation
    -0.44
    abetes
    -0.44
    ]))
    
    -0.43
     "
    -0.43
    cutta
    -0.42
    ()],
    -0.42
    POSITIVE LOGITS
     Efq
    0.75
     Jefus
    0.70
    tvguidetime
    0.66
     uploads
    0.65
     createContext
    0.65
     Tinggi
    0.64
     fubject
    0.64
     ―――――
    0.64
    Personensuche
    0.64
     Diſ
    0.63
    Activations Density 0.114%

    No Known Activations