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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1881
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing and signing up for newsletters or email lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poveznice
    -0.58
     convertView
    -0.58
    HttpContext
    -0.58
    }}}
    -0.56
    lasty
    -0.55
    kuuta
    -0.55
    \}\\
    -0.54
    tablename
    -0.53
     <=",
    -0.53
    ளி
    -0.53
    POSITIVE LOGITS
     newsletter
    0.63
     newsletters
    0.57
     rischi
    0.55
     notifications
    0.54
     soprav
    0.51
     OMITBAD
    0.51
     Notifications
    0.51
     subscription
    0.50
    subscribe
    0.50
     Newsletter
    0.50
    Activations Density 0.124%

    No Known Activations