© 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. 9-GEMMASCOPE-RES-16K
    11. 176
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and comparisons of outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betale
    -0.51
    lenburg
    -0.49
     onCreateView
    -0.49
     Roumanie
    -0.48
     SqlDbType
    -0.48
    ranath
    -0.47
     LUMP
    -0.46
     debole
    -0.46
     inefficient
    -0.45
     للمعارف
    -0.44
    POSITIVE LOGITS
     spared
    0.64
    ьаж
    0.60
     cleanest
    0.58
    MessageTagHelper
    0.58
     smooth
    0.57
     unharmed
    0.56
    NoError
    0.56
     undisturbed
    0.55
     épar
    0.55
     undamaged
    0.54
    Activations Density 0.837%

    No Known Activations