© 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. 23-GEMMASCOPE-RES-16K
    11. 11741
    Prev
    Next
    INDEX
    Explanations

    linguistic features related to ergative and absolutive case markings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.70
     myſelf
    -0.70
     Monfieur
    -0.69
     raiſ
    -0.69
     iſt
    -0.68
     ſta
    -0.66
     ſeveral
    -0.66
     whoſe
    -0.65
     Diſ
    -0.64
     itſelf
    -0.64
    POSITIVE LOGITS
     kasarigan
    0.68
     <=",
    0.67
    hoeddwyd
    0.60
     hit
    0.57
    jsii
    0.57
    @[+][
    0.55
    անում
    0.55
    KURZBESCHREIBUNG
    0.55
     ad
    0.55
     actionPerformed
    0.54
    Activations Density 0.017%

    No Known Activations