© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16064
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intention

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

    expressions of desire or intention, typically where a speaker states that they want to do or have something.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the phrase "I want" or "we want" expressing desires or intentions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    ↵↵↵↵
    -0.43
     Groves
    -0.41
    скоре
    -0.40
     CBC
    -0.40
     Davis
    -0.39
     DD
    -0.38
     Solis
    -0.37
     Harris
    -0.37
     Pier
    -0.37
     Steele
    -0.37
    POSITIVE LOGITS
    want
    1.15
     WANT
    1.08
     want
    1.08
    wants
    1.07
    Want
    1.04
     Want
    0.99
    WANT
    0.95
     wants
    0.93
     Wants
    0.93
    wanted
    0.93
    Activations Density 0.069%

    No Known Activations