© 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. 22-GEMMASCOPE-RES-16K
    11. 12772
    Prev
    Next
    INDEX
    Explanations

    numerical values and their relationships in equations and scientific measurements

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

    Comparison or relation between quantities

    np_acts-logits-general · gemini-2.0-flash

    comparisons with 'is' or 'was'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.59
    хьтан
    -0.53
    mybatisplus
    -0.52
    modelBuilder
    -0.51
     distanciation
    -0.51
     الحره
    -0.51
    intem
    -0.51
    BooleanField
    -0.51
    الدراسه
    -0.49
     насељу
    -0.48
    POSITIVE LOGITS
     equal
    1.06
     greater
    0.97
     larger
    0.90
     smaller
    0.84
    equal
    0.81
    tvguidetime
    0.78
    greater
    0.77
     determined
    0.77
    larger
    0.74
     bigger
    0.73
    Activations Density 1.287%

    No Known Activations