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. 15840
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their achievements

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    proper nouns following a period

    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
     yes
    -0.49
     here
    -0.49
    siger
    -0.48
     natürlich
    -0.46
     ‘
    -0.46
     Yes
    -0.45
     question
    -0.43
     weren
    -0.43
     what
    -0.43
     “
    -0.42
    POSITIVE LOGITS
    ########.
    0.88
    ंदीखरीदारी
    0.88
    WithIOException
    0.80
    Personendaten
    0.79
    findpost
    0.75
    WebElementEntity
    0.75
    balleur
    0.75
    MessageOf
    0.74
    hoeddwyd
    0.74
    ///</
    0.73
    Activations Density 0.346%

    No Known Activations