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. 5302
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific names or characters related to stories or legends

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

    Follows title-case words

    np_acts-logits-general · gemini-2.0-flash

    reported speech and circumstances

    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
    raszamy
    -0.60
    ślę
    -0.59
     principalmente
    -0.57
    mtable
    -0.54
    muerzo
    -0.53
    hacia
    -0.53
    ikita
    -0.53
    primarily
    -0.52
    esterday
    -0.52
    说说
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.72
     wept
    0.70
     accidentally
    0.62
    GEBURTSDATUM
    0.62
     enraged
    0.61
     miraculously
    0.61
    featureID
    0.60
     angeb
    0.59
    ControllerTest
    0.59
     allegedly
    0.59
    Activations Density 0.431%

    No Known Activations