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. 6526
    Prev
    Next
    INDEX
    Explanations

    references to events or opportunities in the technology sector

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

    that come before action or speech

    np_acts-logits-general · gemini-2.0-flash

    sequence of events

    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
    BagLayout
    -0.60
    ControllerAdvice
    -0.58
    ={`/
    -0.57
    RefNanny
    -0.55
    pushFollow
    -0.54
    zise
    -0.53
     Reverso
    -0.53
    IntoConstraints
    -0.53
    ofType
    -0.52
    AndroidJUnit
    -0.52
    POSITIVE LOGITS
     afterwards
    0.88
     afterward
    0.87
     Afterward
    0.82
    Afterwards
    0.78
     Afterwards
    0.72
     danach
    0.71
     utafitiHapana
    0.68
     conclusiones
    0.66
     nachher
    0.65
     follow
    0.61
    Activations Density 0.284%

    No Known Activations