© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 12730
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structural elements in a text, indicating data or references, such as citations and section titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fotografico
    -0.62
    windowFixed
    -0.61
     pleins
    -0.60
     numberOfRows
    -0.60
    ImageContext
    -0.59
     <<<<<<<<<<<<<<
    -0.59
     fören
    -0.58
    chwyd
    -0.58
     informée
    -0.57
     Архів
    -0.54
    POSITIVE LOGITS
     CreateTagHelper
    0.67
    <caption>
    0.51
    hoeddwyd
    0.50
     AssemblyTitle
    0.50
    ViewImports
    0.49
    EndContext
    0.49
    Arnold
    0.46
     Arnold
    0.45
    UnitTesting
    0.45
     насеље
    0.44
    Activations Density 1.141%

    No Known Activations