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. 13-GEMMASCOPE-RES-16K
    6. 14670
    Prev
    Next
    INDEX
    Explanations

    numeric data and parameters related to statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/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.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.90
     "..\..\
    -0.88
     linkovi
    -0.83
     "..\..\..\
    -0.75
    TagMode
    -0.74
    wpi
    -0.73
    脚注の使い方
    -0.73
    contentLoaded
    -0.73
     ostavi
    -0.69
     bezeichneter
    -0.67
    POSITIVE LOGITS
     CreateTagHelper
    0.55
    msgTypes
    0.47
    mockMvc
    0.47
    MockMvc
    0.45
    primaryStage
    0.45
     le
    0.45
     her
    0.45
    évaluateur
    0.43
     is
    0.42
    hagic
    0.42
    Activations Density 0.095%

    No Known Activations