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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15818
    Prev
    Next
    INDEX
    Explanations

    numerical information or statistics

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

    Citations to legal cases

    np_acts-logits-general · gemini-2.0-flash

    legal citations

    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
    HostException
    -0.80
    Tembelea
    -0.73
     autorytatywna
    -0.73
     springfox
    -0.72
    Rhestr
    -0.72
    StoryboardSegue
    -0.72
    URLException
    -0.72
    MENAFN
    -0.66
     nakalista
    -0.65
    PhysRevD
    -0.63
    POSITIVE LOGITS
    almo
    0.48
     afec
    0.41
     Stück
    0.40
     Executive
    0.40
     داره
    0.40
     malos
    0.38
     executive
    0.38
    ########.
    0.38
     nuit
    0.37
    υγ
    0.37
    Activations Density 0.264%

    No Known Activations