© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8355
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and medical conditions, particularly in a research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sullivan
    -0.58
    NewGuid
    -0.57
    Geplaatst
    -0.54
     Callum
    -0.53
     tung
    -0.50
    Sullivan
    -0.49
     Fournier
    -0.48
    zx
    -0.47
     Becher
    -0.47
    DBObject
    -0.47
    POSITIVE LOGITS
     Mar
    3.45
    Mar
    3.27
     MAR
    3.20
     mar
    3.03
    MAR
    2.89
    mar
    2.80
     Мар
    2.27
    Marg
    2.06
    Мар
    1.93
     مار
    1.88
    Activations Density 0.858%

    No Known Activations