© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9157
    Prev
    Next
    INDEX
    Explanations

    references to food, dining experiences, and related elements in various contexts

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

    Preceding words followed by "was" or "is"

    np_acts-logits-general · gemini-2.0-flash

    describing state of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.73
    InputBorder
    -0.70
    esModule
    -0.64
    انيف
    -0.61
    ImageContext
    -0.61
    offsetof
    -0.59
    InjectAttribute
    -0.58
    dflare
    -0.57
     =>
    
    -0.56
    ⓘ
    -0.56
    POSITIVE LOGITS
     sucks
    0.86
     sucked
    0.79
     itself
    0.76
     looked
    0.74
     was
    0.71
     wise
    0.66
     AMAZING
    0.65
     stinks
    0.64
     wasn
    0.64
     seemed
    0.64
    Activations Density 0.105%

    No Known Activations