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. 4026
    Prev
    Next
    INDEX
    Explanations

    important player actions and highlights in sports narratives

    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
     صوتيه
    -0.61
     typelib
    -0.59
    ByDefault
    -0.52
    ingeki
    -0.51
    ⓧ
    -0.50
     précieux
    -0.49
    :+:
    -0.49
    didSet
    -0.49
     Shutter
    -0.48
    IRQn
    -0.48
    POSITIVE LOGITS
     wea
    0.58
     rif
    0.56
    ']),
    0.51
     connected
    0.50
     lof
    0.49
     calmly
    0.49
     capital
    0.49
    Mec
    0.48
     spun
    0.48
     converted
    0.48
    Activations Density 0.141%

    No Known Activations