© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2100
    Prev
    Next
    INDEX
    Explanations

    the infinitive form of verbs at the beginning of phrases

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

    Followed by an infinitive verb

    np_acts-logits-general · gemini-2.0-flash

    "To" plus verb introducing statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -1.01
    thâu
    -0.80
     otomatig
    -0.79
    يكب
    -0.78
    principalColumn
    -0.74
    السكان
    -0.69
    FormTagHelper
    -0.67
     comuniques
    -0.67
     EconPapers
    -0.67
    InjectAttribute
    -0.66
    POSITIVE LOGITS
     quote
    0.83
     date
    0.76
     paraphrase
    0.74
     sum
    0.73
     summarize
    0.68
     recap
    0.66
     complicate
    0.64
     kasarigan
    0.60
     compound
    0.59
     illustrate
    0.57
    Activations Density 0.094%

    No Known Activations