© 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. 16-GEMMASCOPE-RES-16K
    11. 14486
    Prev
    Next
    INDEX
    Explanations

    references to family relationships, particularly in the context of obituaries or memorials

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

    Punctuations and "cost" before certain words

    np_acts-logits-general · gemini-2.0-flash

    concluding punctuation and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.86
    protoimpl
    -0.81
     myſelf
    -0.79
     ſche
    -0.72
     Exacts
    -0.72
    ViewFeatures
    -0.70
    المكان
    -0.70
     iſt
    -0.69
     purpoſe
    -0.67
     itſelf
    -0.67
    POSITIVE LOGITS
    MigrationBuilder
    0.57
    发表于
    0.55
     
    0.54
     numerous
    0.53
    <eos>
    0.52
    })();
    0.48
     great
    0.48
     countless
    0.44
     many
    0.44
     des
    0.43
    Activations Density 0.010%

    No Known Activations