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. 12965
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or representations in the text

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

    Vectors and vector notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical vectors

    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
     memer
    -0.60
    rufen
    -0.55
     Ring
    -0.48
    __;
    -0.47
     open
    -0.47
    kond
    -0.47
     under
    -0.46
    ίδ
    -0.45
     onData
    -0.45
    Искәрмәләр
    -0.45
    POSITIVE LOGITS
     vectors
    0.79
     vettore
    0.73
     vektor
    0.70
     vector
    0.68
     autorytatywna
    0.68
    ########.
    0.66
     벡터
    0.66
     vecteur
    0.65
     vektör
    0.64
    HasAnnotation
    0.63
    Activations Density 0.753%

    No Known Activations