© 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. 15232
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "this" and its variations in context

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

    "This" followed by an auxiliary verb

    np_acts-logits-general · gemini-2.0-flash

    following "This"

    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
    :][
    -0.75
     للاسماء
    -0.74
    ftagPool
    -0.69
     nakalista
    -0.66
    devamını
    -0.64
    awtextra
    -0.61
     slightest
    -0.60
     recent
    -0.60
    writeFieldEnd
    -0.59
    libft
    -0.58
    POSITIVE LOGITS
    ModelBuilder
    0.53
     page
    0.51
     item
    0.46
    WriteBarrier
    0.45
    AdapterFactory
    0.44
    Is
    0.44
     Wikiseite
    0.44
    CreateModel
    0.43
    RegressionTest
    0.42
    tagHelperRunner
    0.42
    Activations Density 0.270%

    No Known Activations