© 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. 20-GEMMASCOPE-RES-16K
    11. 5558
    Prev
    Next
    INDEX
    Explanations

    pronouns and their usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Statements about what someone said they would do

    np_acts-logits-general · gemini-2.0-flash

    subject's feelings and intentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Apparently
    -0.85
    Said
    -0.82
     schein
    -0.81
     reportedly
    -0.81
     apparently
    -0.81
     bezeichneter
    -0.80
    apparently
    -0.80
     Seem
    -0.76
    Apparently
    -0.76
     dikatakan
    -0.76
    POSITIVE LOGITS
     regrets
    0.74
     hopes
    0.71
     expects
    0.69
     feels
    0.68
     hoped
    0.67
     plans
    0.66
     regretted
    0.65
     never
    0.63
     believes
    0.60
     aspetta
    0.60
    Activations Density 0.242%

    No Known Activations