© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12810
    Prev
    Next
    INDEX
    Explanations

    expressions emphasizing particularity or specificity regarding topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     Offline
    -0.44
    bonucle
    -0.43
    inigungs
    -0.43
    AutoField
    -0.42
     offline
    -0.42
     derra
    -0.42
    Offline
    -0.41
    Breite
    -0.40
     toilet
    -0.40
     neem
    -0.39
    POSITIVE LOGITS
     especially
    1.82
    Especially
    1.72
     Especially
    1.70
    especially
    1.64
     particularly
    1.54
     Particularly
    1.45
    particularly
    1.44
     especialmente
    1.41
     Особенно
    1.37
     особенно
    1.36
    Activations Density 0.276%

    No Known Activations