© 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. 2-GEMMASCOPE-RES-16K
    11. 16335
    Prev
    Next
    INDEX
    Explanations

    instances of the word "seemed" and its variations, indicating perceptions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.67
    enskap
    -0.66
    JNIEnv
    -0.58
    marvin
    -0.57
     currently
    -0.56
    leve
    -0.55
    πάρχ
    -0.55
    spaceBetween
    -0.54
     leksikon
    -0.52
     Kiran
    -0.50
    POSITIVE LOGITS
     seemed
    1.26
    seemed
    1.19
     mattered
    1.17
     vardı
    1.10
     Había
    1.10
     resembled
    1.09
    ktı
    1.06
     estava
    1.05
    était
    1.05
     كانت
    1.04
    Activations Density 0.079%

    No Known Activations