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. 5273
    Prev
    Next
    INDEX
    Explanations

    structured data or formatting indicators

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

    Followed by numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical equations and technical terms

    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
     G
    -0.47
     bahkan
    -0.46
     kind
    -0.44
    G
    -0.43
     Sug
    -0.41
     mē
    -0.41
    <eos>
    -0.41
    liz
    -0.41
    cado
    -0.41
     sort
    -0.40
    POSITIVE LOGITS
    :✨
    1.07
     للاسماء
    0.84
     esternos
    0.82
     betweenstory
    0.82
    tvguidetime
    0.81
    writeFieldEnd
    0.81
     oprot
    0.79
    abestanden
    0.78
    rungsseite
    0.78
     Roskov
    0.77
    Activations Density 0.077%

    No Known Activations