© 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. 8-GEMMASCOPE-RES-16K
    6. 4837
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical expressions or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OkHttpClient
    -0.71
    δες
    -0.69
    FetchType
    -0.67
     Zappa
    -0.66
     Satz
    -0.65
     ويكيپيديا
    -0.64
     hansen
    -0.63
    Zara
    -0.62
    Advertisements
    -0.62
    Elen
    -0.62
    POSITIVE LOGITS
     }^{
    1.95
     }^{\
    1.08
     }^{[
    0.93
     }_{
    0.92
     }^{(
    0.88
     }^{-
    0.71
    ης
    0.70
     Ae
    0.69
    sedown
    0.69
     Stodd
    0.67
    Activations Density 0.034%

    No Known Activations