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. 13-GEMMASCOPE-RES-16K
    6. 12388
    Prev
    Next
    INDEX
    Explanations

    text related to bowling titles and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Bảo
    -0.42
     film
    -0.42
     जल
    -0.41
    lwjgl
    -0.40
     por
    -0.40
     cro
    -0.40
     av
    -0.39
     extra
    -0.38
     rad
    -0.38
     Gogh
    -0.38
    POSITIVE LOGITS
     myſelf
    1.06
     itſelf
    1.02
    ########.
    0.98
     initComponents
    0.98
     Efq
    0.98
     насељу
    0.98
     chi̍t
    0.88
     houſe
    0.88
    ſelves
    0.88
    клопе
    0.88
    Activations Density 0.925%

    No Known Activations