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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6500
    Prev
    Next
    INDEX
    Explanations

    special mathematical symbols or notations

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

    Punctuation followed by transition words

    np_acts-logits-general · gemini-2.0-flash

    transition words after punctuation

    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
     Baumann
    -0.67
    Matéri
    -0.65
     Master
    -0.60
     Nug
    -0.59
    tableFuture
    -0.59
    Хьажоргаш
    -0.58
    udadera
    -0.56
    ]()
    -0.56
    ficação
    -0.56
     AsyncTask
    -0.56
    POSITIVE LOGITS
    由此
    0.60
     hence
    0.59
     <=",
    0.59
    因此
    0.57
    也就是说
    0.56
     Furthermore
    0.56
    ivably
    0.56
     Hence
    0.56
     Likewise
    0.56
    DockStyle
    0.55
    Activations Density 0.983%

    No Known Activations