© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 7089
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns related to self-reference

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

    Reflexive pronouns

    np_acts-logits-general · gemini-2.0-flash

    self and selves

    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
    DockStyle
    -0.78
    تیب
    -0.71
    SBATCH
    -0.70
     MessageBoxIcon
    -0.69
     quæ
    -0.69
    astify
    -0.67
    ectady
    -0.67
    StoryboardSegue
    -0.65
    OGND
    -0.62
    ::::::::
    -0.61
    POSITIVE LOGITS
    SELF
    0.89
     SELF
    0.63
    selves
    0.60
    ändig
    0.58
    standig
    0.57
    Self
    0.57
    ELF
    0.57
    skraft
    0.57
     Self
    0.54
     selves
    0.54
    Activations Density 0.058%

    No Known Activations