© 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. 13196
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "describe" and its variations in different contexts

    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
    prnewswire
    -0.62
     يتيمه
    -0.62
    osoever
    -0.58
     imun
    -0.58
    thenReturn
    -0.57
     Accesat
    -0.56
    íncia
    -0.56
     kema
    -0.55
     oxidative
    -0.54
     думал
    -0.54
    POSITIVE LOGITS
     describe
    2.15
     describes
    1.96
     Describe
    1.94
     described
    1.90
    Describe
    1.85
     describing
    1.81
    describe
    1.80
     DESCR
    1.79
     Describes
    1.76
    described
    1.70
    Activations Density 0.101%

    No Known Activations