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. 25-GEMMASCOPE-RES-16K
    6. 5935
    Prev
    Next
    INDEX
    Explanations

    dot-separated sequences or code syntax elements

    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
     is
    -0.54
    -
    -0.51
    _
    -0.51
     are
    -0.48
    --
    -0.47
     to
    -0.47
     (
    -0.46
     -
    -0.45
     e
    -0.44
     body
    -0.44
    POSITIVE LOGITS
    ImageContext
    0.83
    tableFuture
    0.80
    PerformLayout
    0.80
     الاطلاع
    0.79
    LookAnd
    0.78
    awtextra
    0.74
    mybatisplus
    0.73
     bezeichneter
    0.73
    Drawing
    0.72
    GraphicsUnit
    0.72
    Activations Density 0.018%

    No Known Activations