© 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. 3536
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating conditions or comparisons in discussions

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

    Preceding "that"

    np_acts-logits-general · gemini-2.0-flash

    that

    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
    [++
    -0.51
     CreateTagHelper
    -0.46
    SizeF
    -0.46
    nach
    -0.45
    ándo
    -0.44
    awtextra
    -0.43
    indelijk
    -0.43
    enido
    -0.42
    __()
    -0.42
    quels
    -0.41
    POSITIVE LOGITS
     that
    3.42
    that
    2.46
     That
    2.30
    That
    2.29
     THAT
    2.12
     those
    2.06
    THAT
    2.05
    那个
    1.84
    那
    1.79
    那個
    1.77
    Activations Density 2.767%

    No Known Activations