© 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. 16-GEMMASCOPE-RES-16K
    11. 4711
    Prev
    Next
    INDEX
    Explanations

    expressions of desire and intent related to helping others and achieving personal goals

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

    Preceding "to" and following words of desire

    np_acts-logits-general · gemini-2.0-flash

    expressing wants and desires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    temming
    -0.51
    InputBorder
    -0.48
    はじめに
    -0.47
    NORE
    -0.47
     ușor
    -0.47
    mení
    -0.46
    一波
    -0.46
     insuffisamment
    -0.45
    --)
    -0.44
    rophoresis
    -0.44
    POSITIVE LOGITS
    SharedDtor
    0.65
     möglichst
    0.61
    resave
    0.58
    PYX
    0.56
     save
    0.56
     perfection
    0.55
     propOrder
    0.55
    obtenir
    0.54
     nakalista
    0.54
     Ensuring
    0.54
    Activations Density 0.242%

    No Known Activations