© 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. 28-GEMMASCOPE-RES-16K
    11. 3472
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or reluctance in various contexts

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

    "want to" followed by an action

    np_acts-logits-general · gemini-2.0-flash

    don't want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.57
    IsMutable
    -0.55
    AddHtmlAttribute
    -0.53
    enumii
    -0.52
     kasarigan
    -0.52
    PyExc
    -0.44
    InitVars
    -0.44
     consultato
    -0.43
    Distribuzione
    -0.42
     Grüße
    -0.41
    POSITIVE LOGITS
     risking
    0.71
     risk
    0.68
     losing
    0.63
     lose
    0.57
    risk
    0.53
     loosing
    0.53
     perdere
    0.53
     hassle
    0.52
     wasting
    0.52
     spending
    0.52
    Activations Density 0.332%

    No Known Activations