© 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. 18-GEMMASCOPE-RES-16K
    11. 8339
    Prev
    Next
    INDEX
    Explanations

    terms related to enhancement or improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "enhancement" or "enhance"

    np_acts-logits-general · gemini-2.0-flash

    enhancement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    -0.74
    a
    -0.68
    u
    -0.59
     d
    -0.56
    ia
    -0.56
     nam
    -0.53
    ne
    -0.52
    an
    -0.51
    ames
    -0.51
     "
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    1.54
     myſelf
    1.52
     Monfieur
    1.37
     themſelves
    1.35
     itſelf
    1.33
     ſeveral
    1.32
     raiſ
    1.29
     becauſe
    1.28
     purpoſe
    1.27
     Efq
    1.26
    Activations Density 0.173%

    No Known Activations