© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 7651
    Prev
    Next
    INDEX
    Explanations

    probability-related terms and numerical data

    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
    ILayout
    -0.42
    MeasureSpec
    -0.41
    …
    -0.40
     Orten
    -0.39
    gdala
    -0.38
     babak
    -0.37
    getRuntime
    -0.36
    WriteBarrier
    -0.36
    ,‎
    -0.36
     rapat
    -0.35
    POSITIVE LOGITS
    出版年
    1.19
    InjectAttribute
    0.88
     AssemblyTitle
    0.88
    RegressionTest
    0.86
     betweenstory
    0.78
    تقاوى
    0.76
     noDo
    0.76
     Roskov
    0.76
     يتيمه
    0.74
    Datuak
    0.73
    Activations Density 0.490%

    No Known Activations