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. 19-GEMMASCOPE-RES-16K
    6. 15704
    Prev
    Next
    INDEX
    Explanations

    guidelines for formal introductions and name usage in social or business contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.80
     فريبيس
    -0.73
    BufferException
    -0.67
    المشاركات
    -0.67
    aarrggbb
    -0.67
    ]))
    
    -0.64
    CPtr
    -0.59
    </thead>
    -0.59
    ########.
    -0.58
     ThemeData
    -0.58
    POSITIVE LOGITS
     surname
    1.16
    surname
    0.94
     nickname
    0.92
     surnames
    0.88
     nicknames
    0.88
     titles
    0.86
    apellido
    0.86
     Surname
    0.86
     title
    0.83
     Titles
    0.82
    Activations Density 0.121%

    No Known Activations