© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15808
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal desire and agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    colgroup
    -0.38
    NOWLEDG
    -0.32
     देने
    -0.32
    spyOn
    -0.30
     мәкал
    -0.30
    testens
    -0.29
    vědět
    -0.29
    SharedDtor
    -0.29
    TestBed
    -0.29
    Expecting
    -0.28
    POSITIVE LOGITS
     pleases
    1.13
     pleased
    0.95
     please
    0.95
     whim
    0.85
    please
    0.82
     liking
    0.80
     pleaf
    0.78
     pleasure
    0.77
     PLEASE
    0.75
     deems
    0.73
    Activations Density 0.260%

    No Known Activations