© 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. 15-GEMMASCOPE-RES-16K
    11. 9018
    Prev
    Next
    INDEX
    Explanations

    expectation statements related to function evaluations in JavaScript code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.91
     beginnetje
    -0.83
    Geplaatst
    -0.75
    
    -0.74
    fjspx
    -0.74
    extAlignment
    -0.72
    jsxFileName
    -0.72
    OGND
    -0.72
    bewerken
    -0.72
     tartalomajánló
    -0.71
    POSITIVE LOGITS
    assertThat
    0.67
    expect
    0.57
     overall
    0.52
     it
    0.47
     emlé
    0.47
    overall
    0.46
     THINK
    0.46
    assertEqual
    0.45
    囱
    0.45
    javadoc
    0.45
    Activations Density 0.084%

    No Known Activations