© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1893
    Prev
    Next
    INDEX
    Explanations

    phrases related to purpose or intent in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    бочки
    -0.44
     sought
    -0.41
    ta
    -0.40
    tha
    -0.40
    clean
    -0.40
    égard
    -0.40
    では
    -0.39
    Limit
    -0.38
    hoy
    -0.38
    ady
    -0.38
    POSITIVE LOGITS
    dafx
    0.92
    WithIOException
    0.83
    GEBURTSDATUM
    0.81
    IUrlHelper
    0.80
    SuccessListener
    0.79
    Vidite
    0.76
     Roskov
    0.72
    发表于
    0.72
     للمعارف
    0.71
     ComVisible
    0.71
    Activations Density 0.208%

    No Known Activations