© 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 EvalsExportsinterp-engineNEWAPI 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. 10809
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific trials and studies

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

    Subject of a sentence

    np_acts-logits-general · gemini-2.0-flash

    things becoming or happening

    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
    ArgsConstructor
    -0.81
     onlyOwner
    -0.78
    ########.
    -0.74
     telah
    -0.72
     đã
    -0.72
     NavController
    -0.72
    CppCodeGen
    -0.72
     Numerade
    -0.71
     autorytatywna
    -0.70
    __":
    -0.69
    POSITIVE LOGITS
     becomes
    1.18
     gets
    1.07
     develops
    0.94
     goes
    0.91
     become
    0.87
    becomes
    0.85
     decides
    0.83
     succeeds
    0.80
     nanti
    0.79
     reaches
    0.78
    Activations Density 0.500%

    No Known Activations