© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1271
    Prev
    Next
    INDEX
    Explanations

    references to people and their interactions in a narrative context

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

    Follows a person/pronoun who is speaking

    np_acts-logits-general · gemini-2.0-flash

    reporting speech and dialogue

    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
    interopRequire
    -0.77
    OrNil
    -0.55
    StoryboardSegue
    -0.53
    Cubit
    -0.51
    SBATCH
    -0.48
    Ranks
    -0.47
    Threading
    -0.47
     genero
    -0.44
    ACTED
    -0.44
    lnie
    -0.43
    POSITIVE LOGITS
     saying
    2.08
     said
    2.07
     say
    1.96
     says
    1.89
    Said
    1.75
    said
    1.72
    saying
    1.70
     Said
    1.66
     Says
    1.62
     berkata
    1.61
    Activations Density 0.305%

    No Known Activations