© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27911
    Prev
    Next
    INDEX
    Explanations

    mentions of candy and related sweet food items

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

    candy and Halloween treats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']))
    -0.97
     --}}
    -0.85
     }^{*}$
    -0.78
    '])){
    -0.77
     SwitchCompat
    -0.75
    Vader
    -0.74
    endphp
    -0.74
    "),
    -0.73
    }],
    -0.73
    */}
    -0.72
    POSITIVE LOGITS
     candy
    1.14
     Candy
    1.00
    Candy
    0.90
    candy
    0.88
     candies
    0.85
     Dandy
    0.68
     dandy
    0.66
    flashdata
    0.63
    aarrggbb
    0.63
    hiza
    0.63
    Activations Density 0.005%

    No Known Activations