© 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. 14791
    Prev
    Next
    INDEX
    Explanations

    references to the manner or fashion in which actions or processes occur

    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
     Theſe
    -0.81
     Demet
    -0.67
     Houſe
    -0.65
     Diretto
    -0.64
     leaſt
    -0.63
     Conſ
    -0.62
     Shaksp
    -0.62
     theſe
    -0.61
     Perſ
    -0.60
    らなかった
    -0.59
    POSITIVE LOGITS
     ligiloj
    0.74
     ControllerBase
    0.66
    ViewImports
    0.65
     vainilla
    0.60
     Audiodateien
    0.59
     AssemblyTitle
    0.59
     CreateTagHelper
    0.58
    XmlAccessType
    0.57
    ElementException
    0.57
     Scotia
    0.57
    Activations Density 0.587%

    No Known Activations