© 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. 11296
    Prev
    Next
    INDEX
    Explanations

    derogatory terms associated with intelligence or decision-making

    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
    aspectj
    -0.76
     springfox
    -0.73
    TagHelper
    -0.71
    :✨
    -0.70
     ExecuteAsync
    -0.69
    orteur
    -0.65
     lenker
    -0.61
     "}";
    -0.61
     Процитовано
    -0.60
     FINDINGS
    -0.60
    POSITIVE LOGITS
     stupid
    2.86
    stupid
    2.55
     Stupid
    2.46
     dumb
    2.33
    Stupid
    2.32
     silly
    2.28
     foolish
    2.18
     stupidity
    2.17
     idiotic
    2.15
     idiot
    2.12
    Activations Density 0.186%

    No Known Activations