© 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. 16015
    Prev
    Next
    INDEX
    Explanations

    references to political events and figures

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

    Text following punctuation

    np_acts-logits-general · gemini-2.0-flash

    communist threat, cells, children

    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
     gotta
    -0.53
    _'.$
    -0.48
    liosis
    -0.45
     Gotta
    -0.45
    Everybody
    -0.44
     empuj
    -0.43
    ilí
    -0.43
    咋
    -0.42
    Anybody
    -0.42
    viewDidLoad
    -0.42
    POSITIVE LOGITS
     Enclosed
    1.03
     herewith
    0.90
     undersigned
    0.90
     enclosed
    0.85
    tagHelperRunner
    0.84
    Kindly
    0.82
    Yours
    0.82
     kindly
    0.81
     Yours
    0.80
    migrationBuilder
    0.80
    Activations Density 0.217%

    No Known Activations