© 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. 18-GEMMASCOPE-RES-16K
    11. 1589
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their associated contexts within sentences

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

    Follows commas or introduces quotations

    np_acts-logits-general · gemini-2.0-flash

    Selective coupling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unknownFields
    -0.80
    findpost
    -0.74
    ContentAsync
    -0.72
    )++;
    -0.71
     esternos
    -0.69
    
    -0.69
    KommentareTeilen
    -0.68
    contentLoaded
    -0.68
     hefyd
    -0.67
     CreateTagHelper
    -0.67
    POSITIVE LOGITS
     according
    1.02
    according
    0.80
    According
    0.67
     menurut
    0.65
     said
    0.64
     según
    0.64
     selon
    0.64
     officials
    0.60
    said
    0.59
     volgens
    0.55
    Activations Density 0.123%

    No Known Activations