© 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. 22-GEMMASCOPE-RES-16K
    11. 11461
    Prev
    Next
    INDEX
    Explanations

    the use of the first-person perspective in narratives

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

    "I think" or expressing an opinion

    np_acts-logits-general · gemini-2.0-flash

    I think, believe, remember

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.70
    RenderAtEndOf
    -0.66
     lenker
    -0.64
     onPostExecute
    -0.63
     Meksiku
    -0.61
     themſelves
    -0.60
     pleaſure
    -0.59
     oldValue
    -0.58
     himſelf
    -0.56
     gratitude
    -0.56
    POSITIVE LOGITS
     remember
    0.97
     recall
    0.88
    remember
    0.74
     memory
    0.74
     recollect
    0.73
     Remember
    0.71
     mémoire
    0.70
     IIRC
    0.69
     recollection
    0.69
    memory
    0.68
    Activations Density 0.173%

    No Known Activations