© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6144
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or possession

    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
    rible
    -0.56
    šanās
    -0.53
    goku
    -0.51
     riuscito
    -0.51
    ättä
    -0.50
     etme
    -0.48
    Elijah
    -0.47
     Stockholm
    -0.47
    Sey
    -0.47
    használ
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.89
    ########.
    0.89
    WriteTagHelper
    0.89
    ftagPool
    0.89
    AndEndTag
    0.81
    ModelSerializer
    0.76
     BorderRadius
    0.76
    ArgsConstructor
    0.75
    IGraphics
    0.75
     EconPapers
    0.74
    Activations Density 0.876%

    No Known Activations