Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 706
    Prev
    Next
    INDEX
    Explanations

    instances of the word "most" indicating significance or superlative qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     umbro
    -0.77
    eraard
    -0.71
    väg
    -0.70
    ktm
    -0.70
     pauvre
    -0.69
     ſche
    -0.69
     cualquiera
    -0.66
     capilar
    -0.66
     médié
    -0.66
    VideoCapture
    -0.65
    POSITIVE LOGITS
     most
    1.01
     Moreno
    0.77
    ็จ
    0.74
     meest
    0.73
     amount
    0.73
    MOST
    0.71
    +#+#
    0.71
     MOST
    0.70
    ❹
    0.70
    ).</
    0.69
    Activations Density 0.040%

    No Known Activations