© 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. 20-GEMMASCOPE-RES-16K
    11. 6126
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic research applications and guidelines

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

    Acknowledgments or expressions of gratitude

    np_acts-logits-general · gemini-2.0-flash

    special issue thanks environment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     credere
    -0.62
     AssemblyTitle
    -0.62
     techs
    -0.56
     دیگه
    -0.56
     prouver
    -0.54
     Manufacturer
    -0.52
     prouve
    -0.52
     طبق
    -0.50
     beginnetje
    -0.50
    TypedDataSet
    -0.49
    POSITIVE LOGITS
     colleagues
    0.79
     colleague
    0.76
     Fellows
    0.75
     broadly
    0.74
     substantive
    0.72
    nocześnie
    0.71
     convened
    0.65
    くださった
    0.63
    かわらず
    0.63
    териалы
    0.63
    Activations Density 0.610%

    No Known Activations