© 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 - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9879
    Prev
    Next
    INDEX
    Explanations

    the repetition of the Chinese character "在" and related fill instructions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.68
    extAlignment
    -0.68
    IMDG
    -0.65
    matorium
    -0.63
    boutin
    -0.61
    Extinguishing
    -0.60
    Erreferentziak
    -0.60
    Notae
    -0.59
    Manbalar
    -0.59
    Termine
    -0.58
    POSITIVE LOGITS
    fill
    1.07
     fill
    1.04
    Fill
    0.87
     Fill
    0.81
    在
    0.76
    AnimationsModule
    0.68
    가
    0.64
     createSlice
    0.64
    GEBURTSDATUM
    0.62
    GeneratedValue
    0.62
    Activations Density 0.026%

    No Known Activations