© 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. 18-GEMMASCOPE-RES-16K
    11. 506
    Prev
    Next
    INDEX
    Explanations

    specialized systems, methods, or designs tailored for specific tasks or purposes

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

    Expressing dedication or specialization

    np_acts-logits-general · gemini-2.0-flash

    specifically designed or dedicated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roek
    -0.60
    IContainer
    -0.52
    帖最后由
    -0.52
    UnknownFields
    -0.51
    enterOuterAlt
    -0.49
    RegressionTest
    -0.48
    tvguidetime
    -0.48
    MarshalTo
    -0.48
    bootstrapcdn
    -0.48
    Expedia
    -0.48
    POSITIVE LOGITS
     dedicated
    2.28
    dedicated
    2.07
     special
    1.98
     specially
    1.92
     specialized
    1.87
    专门
    1.83
    special
    1.80
    Dedicated
    1.79
     Dedicated
    1.77
     specialised
    1.75
    Activations Density 0.440%

    No Known Activations