© 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. 16-GEMMASCOPE-RES-16K
    11. 14559
    Prev
    Next
    INDEX
    Explanations

    references to postal services or mailing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting with "post-", "posts", or "post"

    np_acts-logits-general · gemini-2.0-flash

    post-compound words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    
    -1.17
    SpringBootTest
    -1.04
     XCTest
    -1.01
     Мексичка
    -1.01
     ligiloj
    -0.98
    DockStyle
    -0.98
     AssemblyVersion
    -0.91
    migrationBuilder
    -0.90
    ResumeLayout
    -0.87
    continence
    -0.85
    POSITIVE LOGITS
     Post
    1.48
     POST
    1.45
    Post
    1.40
    post
    1.37
     posts
    1.35
     post
    1.35
     Posts
    1.35
    POST
    1.32
    Posts
    1.25
     getPost
    1.21
    Activations Density 0.118%

    No Known Activations