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. 5-GEMMASCOPE-RES-16K
    6. 13402
    Prev
    Next
    INDEX
    Explanations

    phrases related to data analysis and experimentation in statistical research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.61
     القرن
    -0.57
    addGap
    -0.55
    ftagPool
    -0.53
     saites
    -0.53
    DialogInterface
    -0.53
     actuelles
    -0.52
    enumii
    -0.52
    NetworkInfo
    -0.52
    ularity
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.62
     sample
    0.60
    TestingModule
    0.57
     виправивши
    0.56
    beispiel
    0.53
     example
    0.53
    サンプル
    0.52
    peda
    0.51
     Example
    0.51
    ربای
    0.51
    Activations Density 1.623%

    No Known Activations