© 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. 3703
    Prev
    Next
    INDEX
    Explanations

    instances of the word "get" and its variations, indicating a focus on actions related to obtaining or engaging with something

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

    "Get" followed by an action/state

    np_acts-logits-general · gemini-2.0-flash

    get and prepare

    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
    MigrationBuilder
    -1.06
     noDo
    -0.69
    Personendaten
    -0.68
     препратки
    -0.66
     NSCoder
    -0.66
    сылкі
    -0.64
    wapV
    -0.63
    >{@
    -0.63
    Pautan
    -0.62
    ########.
    -0.62
    POSITIVE LOGITS
     started
    0.82
     ready
    0.73
     acquainted
    0.69
     moving
    0.68
    started
    0.64
     involved
    0.64
    Started
    0.63
     Started
    0.62
     creative
    0.62
     going
    0.60
    Activations Density 0.067%

    No Known Activations