© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9731
    Prev
    Next
    INDEX
    Explanations

    references to academic titles and roles, particularly related to professors and their qualifications

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

    Colloquial or informal language

    np_acts-logits-general · gemini-2.0-flash

    goin' and gettin'

    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
    ]--;
    -0.84
    Geplaatst
    -0.84
    ंदीखरीदारी
    -0.79
    abestanden
    -0.77
    kháu
    -0.76
    verwijspagina
    -0.75
     Baillargeon
    -0.71
     itſelf
    -0.69
     Meksiku
    -0.69
    __":
    -0.69
    POSITIVE LOGITS
     gonna
    1.12
     gettin
    1.11
     ain
    1.10
     lookin
    1.06
    gonna
    1.02
     somethin
    0.99
     GONNA
    0.99
     goin
    0.97
     Gonna
    0.97
     makin
    0.96
    Activations Density 0.252%

    No Known Activations