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. 10-GEMMASCOPE-RES-16K
    6. 10865
    Prev
    Next
    INDEX
    Explanations

    data related to errors and error codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.62
    (||
    -0.56
     ब्रेकडाउन
    -0.55
    NameInMap
    -0.53
     Bezirk
    -0.51
     comets
    -0.51
    orno
    -0.51
     mica
    -0.50
    esca
    -0.50
    Leírás
    -0.50
    POSITIVE LOGITS
    Personendaten
    0.69
    autorest
    0.66
    onViewCreated
    0.65
     Roskov
    0.64
     المعيارى
    0.58
    FailureListener
    0.57
     lenker
    0.54
    سلحة
    0.53
    ForValue
    0.53
    netinet
    0.52
    Activations Density 0.187%

    No Known Activations