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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 1938
    Prev
    Next
    INDEX
    Explanations

    technical terms related to research and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ostensibly
    -0.63
    ंदीखरीदारी
    -0.63
    FWIW
    -0.63
     decidedly
    -0.62
     étui
    -0.60
     toutefois
    -0.60
     saurait
    -0.60
     insofar
    -0.59
    Perhaps
    -0.59
     Conversely
    -0.58
    POSITIVE LOGITS
     few
    0.99
     different
    0.99
    different
    0.84
     researches
    0.81
     equipments
    0.80
    Few
    0.80
     متعلقه
    0.79
     evidences
    0.77
     them
    0.75
    few
    0.75
    Activations Density 1.305%

    No Known Activations