© 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. 24-GEMMASCOPE-RES-16K
    6. 13849
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and ingredient measurements

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

    Cooking ingredients (spices)

    np_acts-logits-general · gemini-2.0-flash

    salt and pepper

    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
     referenties
    -0.73
    phere
    -0.56
    struktion
    -0.56
     client
    -0.53
    tetés
    -0.53
    tencent
    -0.52
    valdo
    -0.49
    Ỗ
    -0.48
    pheres
    -0.47
    ometra
    -0.47
    POSITIVE LOGITS
     pepper
    1.01
     spice
    0.95
     spices
    0.89
    spice
    0.85
    ]")]
    0.84
     cayenne
    0.79
     Spice
    0.79
     Pepper
    0.79
    pepper
    0.77
     Spices
    0.75
    Activations Density 0.137%

    No Known Activations