Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6214
    Prev
    Next
    INDEX
    Explanations

    instances of the word "want" and its variations, indicating desires or wishes

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

    Sentences including the word "want"

    np_acts-logits-general · gemini-2.0-flash

    expressing desire

    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
     كومونز
    -0.79
     MainAxisSize
    -0.79
    SourceChecksum
    -0.73
     OMITTED
    -0.72
     contextLoads
    -0.72
    JNIEnv
    -0.71
    CodedInputStream
    -0.71
     transfieras
    -0.70
     faptul
    -0.68
     Roskov
    -0.68
    POSITIVE LOGITS
     want
    0.86
     Wants
    0.82
     wants
    0.77
     nothing
    0.71
     WANT
    0.69
    wants
    0.68
     wanted
    0.67
    want
    0.66
     Want
    0.63
     us
    0.61
    Activations Density 0.104%

    No Known Activations