© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28332
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and quotations

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

    mathematical calculations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    GEBURTSDATUM
    -1.01
     BorderRadius
    -0.89
    +#+#
    -0.85
     GenerationType
    -0.84
    ManagedBean
    -0.81
    ConstraintMaker
    -0.78
    UpInside
    -0.77
    TagMode
    -0.77
     IndexPath
    -0.75
    WriteTagHelper
    -0.72
    POSITIVE LOGITS
    <eos>
    0.96
    ↵↵
    0.72
    ↵
    0.58
    ↵↵↵↵
    0.57
     kasarigan
    0.57
    willReturn
    0.57
    ↵↵↵↵↵
    0.51
     decât
    0.49
     noires
    0.49
     You
    0.48
    Activations Density 0.063%

    No Known Activations