© 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. 3-GEMMASCOPE-RES-16K
    11. 9944
    Prev
    Next
    INDEX
    Explanations

    references to anti-adhesion or anti-inflammatory substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.80
    URLException
    -0.79
    LabelTagHelper
    -0.76
     beginnetje
    -0.76
     FishBase
    -0.75
    zzlies
    -0.74
     Lauf
    -0.70
    OGND
    -0.67
     magasiner
    -0.66
     متعلقه
    -0.66
    POSITIVE LOGITS
     anti
    3.22
     Anti
    3.12
    Anti
    3.03
    anti
    2.76
     ANTI
    2.60
    ANTI
    2.33
     анти
    2.18
    Анти
    2.17
     Анти
    2.11
     antis
    1.98
    Activations Density 0.089%

    No Known Activations