© 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. 2670
    Prev
    Next
    INDEX
    Explanations

    key phrases or terms relating to analysis and oversight in documentation or data

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

    Followed by the word "is" (or a translation of "is")

    np_acts-logits-general · gemini-2.0-flash

    copula verb constructions

    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
     typelib
    -0.77
    makeText
    -0.69
    >>()
    -0.66
    principalColumn
    -0.65
    sizeCache
    -0.59
    mybatisplus
    -0.57
     />}
    -0.56
    MigrationBuilder
    -0.55
    Referencer
    -0.54
    ','',
    -0.51
    POSITIVE LOGITS
     is
    1.42
     adalah
    1.34
    的是
    1.27
     ialah
    1.25
    คือ
    1.25
    的就是
    1.25
     คือ
    0.99
     là
    0.99
    なのが
    0.96
     are
    0.95
    Activations Density 0.649%

    No Known Activations