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. 11-GEMMASCOPE-RES-16K
    6. 13719
    Prev
    Next
    INDEX
    Explanations

    references to testing frameworks and their associated components in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.72
    帖最后由
    -0.71
     professionali
    -0.68
     gynhyrchwyd
    -0.68
    UnsafeEnabled
    -0.59
    Dari
    -0.56
     ostavi
    -0.54
    dari
    -0.53
     PLWABN
    -0.52
    νες
    -0.52
    POSITIVE LOGITS
    junit
    2.92
     junit
    1.29
     NUnit
    1.22
    UnitTesting
    1.12
     Xunit
    1.06
    JUnit
    1.06
     nonatomic
    1.04
     linkovi
    0.90
     pytest
    0.89
     unittest
    0.83
    Activations Density 0.026%

    No Known Activations