Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 16197
    Prev
    Next
    INDEX
    Explanations

    forms of documentation and formal processes related to submissions and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.80
     BoxDecoration
    -0.79
    UnitTesting
    -0.78
    +:+
    -0.75
    SourceChecksum
    -0.73
    WriteBarrier
    -0.71
    __(/*!
    -0.70
     XCTest
    -0.67
     viewDidLoad
    -0.67
     CommandType
    -0.66
    POSITIVE LOGITS
     form
    0.88
     Form
    0.82
     filled
    0.79
     forms
    0.79
    Form
    0.78
     filling
    0.77
     fill
    0.76
     Fill
    0.73
     FORM
    0.73
     Forms
    0.71
    Activations Density 0.276%

    No Known Activations