© 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. 8311
    Prev
    Next
    INDEX
    Explanations

    expressions related to mathematical calculations and assignments

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

    Followed by a single letter variable

    np_acts-logits-general · gemini-2.0-flash

    give evaluated expressions

    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
     nemlig
    -0.78
    存于互联网档案馆
    -0.73
     nämlich
    -0.71
    SequentialGroup
    -0.69
     bowiem
    -0.68
    Brainz
    -0.68
    SourceChecksum
    -0.66
    сылкі
    -0.65
    DebuggerNonUser
    -0.64
     AssemblyProduct
    -0.63
    POSITIVE LOGITS
     your
    0.79
     yourself
    0.69
    your
    0.66
     yourselves
    0.61
    あなたが
    0.59
     appropriate
    0.57
     Explain
    0.57
    Explain
    0.56
     Yourself
    0.55
     iyong
    0.54
    Activations Density 0.619%

    No Known Activations