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. 1659
    Prev
    Next
    INDEX
    Explanations

    mentions of dates and related terminology

    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
     يتيمه
    -0.68
    Rohy
    -0.62
     HasFactory
    -0.53
    texttt
    -0.52
     pinulongan
    -0.51
     contextLoads
    -0.51
    外部リンク
    -0.49
    esez
    -0.49
    المناصب
    -0.49
    RegistryLite
    -0.48
    POSITIVE LOGITS
    athlon
    0.53
    iding
    0.51
    acorn
    0.50
    viewDidLoad
    0.48
     JButton
    0.47
    Titled
    0.45
    LookAnd
    0.45
    panou
    0.44
    ades
    0.44
    apolis
    0.43
    Activations Density 0.180%

    No Known Activations