© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 208
    Prev
    Next
    INDEX
    Explanations

    scientific and statistical terms related to research and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.94
    Personendaten
    -0.86
    Демографія
    -0.84
     متعلقه
    -0.83
     ſtate
    -0.83
    évaluateur
    -0.82
     purpoſe
    -0.79
    исленность
    -0.77
     faſt
    -0.77
     pleaſure
    -0.77
    POSITIVE LOGITS
     also
    1.03
    also
    0.86
     también
    0.83
     other
    0.81
    Also
    0.77
     aussi
    0.74
     Also
    0.72
     também
    0.70
     też
    0.68
    También
    0.68
    Activations Density 0.747%

    No Known Activations