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. 14-GEMMASCOPE-RES-16K
    6. 10754
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to biological functions and processes

    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
     betweenstory
    -0.91
    دانشنامهٔ
    -0.91
    ViewFeatures
    -0.79
     noDo
    -0.69
    EndGlobalSection
    -0.68
    @[+][
    -0.67
     SwitchCompat
    -0.65
    principalTable
    -0.65
    RegressionTest
    -0.63
     beginnetje
    -0.62
    POSITIVE LOGITS
    #+#
    0.80
     للمعارف
    0.78
    Tembelea
    0.62
    🏼
    0.59
     bowiem
    0.56
    '],
    
    0.56
     ModelExpression
    0.55
     BoxDecoration
    0.55
    ագրություններ
    0.54
     Counselling
    0.53
    Activations Density 2.480%

    No Known Activations