© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9578
    Prev
    Next
    INDEX
    Explanations

    mentions of culinary experiences and diverse food cultures

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

    personal "taste" or preferences

    np_acts-logits-general · gemini-2.0-flash

    taste and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.43
    kháu
    -0.43
     performed
    -0.41
    spyOn
    -0.41
     jit
    -0.40
    hind
    -0.40
    不安
    -0.40
     straff
    -0.39
    Fact
    -0.39
    __*/
    -0.39
    POSITIVE LOGITS
     taste
    1.45
     tastes
    1.41
    taste
    1.19
     preferences
    1.18
     Taste
    1.14
    Taste
    1.07
     appreciation
    1.06
     conno
    1.04
     preference
    1.03
     gustos
    1.03
    Activations Density 0.207%

    No Known Activations