© 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. 21-GEMMASCOPE-RES-16K
    11. 15396
    Prev
    Next
    INDEX
    Explanations

    contextual references to sacred texts and their interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     कार
    -0.47
    __;
    -0.46
    SpringRunner
    -0.44
     Devlin
    -0.43
    ome
    -0.42
     Gough
    -0.41
     въз
    -0.41
     Maynard
    -0.41
    umacher
    -0.40
    Chham
    -0.40
    POSITIVE LOGITS
     Moses
    0.88
    Moses
    0.83
     Exodus
    0.83
    Exodus
    0.81
     CreateTagHelper
    0.79
     Aaron
    0.78
     Levi
    0.78
     Mosaic
    0.77
     Sinai
    0.77
    Mosaic
    0.74
    Activations Density 0.110%

    No Known Activations