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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1481
    Prev
    Next
    INDEX
    Explanations

    occurrences of code-related terminology and formatting issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.60
    :✨
    -0.58
     étudier
    -0.51
    openqa
    -0.47
     estudar
    -0.47
    BackStack
    -0.46
    analy
    -0.46
     quæ
    -0.46
     estud
    -0.46
    crollView
    -0.46
    POSITIVE LOGITS
     format
    1.30
    format
    1.22
     Format
    1.20
     formatting
    1.14
    Format
    1.11
     formatted
    1.07
     formats
    1.05
     FORMAT
    1.05
     Formatting
    1.03
     formatter
    1.00
    Activations Density 0.309%

    No Known Activations