© 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. 8986
    Prev
    Next
    INDEX
    Explanations

    elements related to medical treatments and their effectiveness

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

    followed by "of", "to", "for", or ","

    np_acts-logits-general · gemini-2.0-flash

    rates, barriers, criteria, standard, kinetics, contract

    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
     createSlice
    -0.58
    ($__
    -0.53
     
    -0.47
     Will
    -0.47
     Her
    -0.45
    createClass
    -0.45
     v
    -0.44
    пові
    -0.43
     intptr
    -0.43
     G
    -0.43
    POSITIVE LOGITS
     privind
    0.97
    ในการ
    0.90
     ainfi
    0.88
     vectorielles
    0.80
     relatifs
    0.79
     regarding
    0.76
     myſelf
    0.76
     titolata
    0.75
     ListNode
    0.75
     plufieurs
    0.73
    Activations Density 1.330%

    No Known Activations