© 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. 8109
    Prev
    Next
    INDEX
    Explanations

    words and terms related to "emulsion" and its derivatives

    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
    ########.
    -0.94
     useParams
    -0.79
    Patti
    -0.71
     BoxDecoration
    -0.71
     Knud
    -0.69
     lank
    -0.69
     PLW
    -0.69
     Lipschitz
    -0.69
    casian
    -0.68
     Anſ
    -0.68
    POSITIVE LOGITS
     Em
    3.02
    em
    2.94
    Em
    2.87
     em
    2.79
    EM
    2.39
     EM
    2.26
     Emb
    1.65
    ems
    1.55
    Emb
    1.49
     emulation
    1.37
    Activations Density 0.169%

    No Known Activations