© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 15422
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming languages and code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓘ
    -0.48
    spaceBetween
    -0.42
    himi
    -0.38
    MockBean
    -0.38
    ListTile
    -0.35
    رة
    -0.35
     of
    -0.35
    <strong>
    -0.34
    jedis
    -0.34
    าร
    -0.34
    POSITIVE LOGITS
    ContentAsync
    0.85
    rawDesc
    0.83
    MigrationBuilder
    0.80
     code
    0.75
    bonucleic
    0.75
    UserScript
    0.74
    Chham
    0.74
    InstrumentedTest
    0.73
     Vikipedi
    0.73
     snippetHide
    0.72
    Activations Density 0.868%

    No Known Activations