Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 15685
    Prev
    Next
    INDEX
    Explanations

    references to various groups and their characteristics or actions

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

    preceding "that," "who," or "which."

    np_acts-logits-general · gemini-2.0-flash

    relative clauses describing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectMocks
    -0.60
     tenemos
    -0.56
     mentioned
    -0.52
     situato
    -0.51
     nächste
    -0.50
     hablando
    -0.49
     from
    -0.49
     dizendo
    -0.47
     tienes
    -0.47
     tengo
    -0.46
    POSITIVE LOGITS
    TagHelper
    1.02
     kaarangay
    0.80
     resourceCulture
    0.80
    ArrowToggle
    0.75
    SequentialGroup
    0.74
    elemField
    0.74
    
    0.73
    ViewFeatures
    0.73
    GEBURTSDATUM
    0.72
    ]]);
    0.72
    Activations Density 0.316%

    No Known Activations