Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3771
    Prev
    Next
    INDEX
    Explanations

    conjunctions and qualifiers that express contrast or exceptions

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

    Sentences starting with "but"

    np_acts-logits-general · gemini-2.0-flash

    positive resolutions after "but"

    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
     Exactos
    -0.66
     Exacts
    -0.66
     snippetHide
    -0.64
     Loser
    -0.64
    kháu
    -0.60
    bufio
    -0.60
     👎
    -0.60
    IBAction
    -0.59
    iterranée
    -0.57
     متعلقه
    -0.57
    POSITIVE LOGITS
     fortunately
    0.90
     luckily
    0.86
     зато
    0.80
     thankfully
    0.79
    好在
    0.78
    なんとか
    0.76
     compensated
    0.72
    还好
    0.71
    幸好
    0.71
    何とか
    0.69
    Activations Density 0.263%

    No Known Activations