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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20-GEMMASCOPE-RES-16K
    6. 5155
    Prev
    Next
    INDEX
    Explanations

    keywords and syntax related to programming functions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets using parentheses and periods

    np_acts-logits-general · gemini-2.0-flash

    method calls with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sauvage
    -0.53
    Draws
    -0.52
     pageNum
    -0.52
     userList
    -0.51
     scolaire
    -0.48
     tackling
    -0.48
    cutting
    -0.47
     confiscation
    -0.47
     weeding
    -0.47
    FORMAN
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.87
     referenties
    0.86
     AssemblyTitle
    0.86
    Personendaten
    0.83
     Administrativna
    0.81
    rungsseite
    0.81
     invokingState
    0.81
     ModelExpression
    0.81
     intptr
    0.79
     propOrder
    0.78
    Activations Density 0.244%

    No Known Activations