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. 8-GEMMASCOPE-RES-16K
    6. 8187
    Prev
    Next
    INDEX
    Explanations

    references to divine beings and elements associated with spirituality and the afterlife

    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
    RenderAtEndOf
    -0.83
    verwijspagina
    -0.75
    SourceChecksum
    -0.73
     AssemblyProduct
    -0.64
    jgl
    -0.61
    脚注の使い方
    -0.61
    orale
    -0.56
     Combien
    -0.56
    EndGlobalSection
    -0.55
    varargin
    -0.54
    POSITIVE LOGITS
     heaven
    0.96
     heavenly
    0.90
    Heavenly
    0.89
     angels
    0.86
    heaven
    0.82
     HEAVEN
    0.81
     heavens
    0.80
     Heaven
    0.80
     clouds
    0.79
     angel
    0.76
    Activations Density 0.326%

    No Known Activations