© 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. 15379
    Prev
    Next
    INDEX
    Explanations

    references to a particular type of equipment or merchandise

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

    Plural pronouns and related verbs

    np_acts-logits-general · gemini-2.0-flash

    demonstrative pronouns, them, new, pairs

    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
    principalColumn
    -0.86
     resourceCulture
    -0.85
     CreateTagHelper
    -0.79
    />";
    -0.77
     Monfieur
    -0.75
    EndInit
    -0.75
     LoginComponent
    -0.73
    UIControlState
    -0.71
    الحياه
    -0.71
    %");
    -0.70
    POSITIVE LOGITS
     these
    1.16
     those
    1.08
     These
    1.07
     them
    1.02
    These
    1.02
    these
    1.00
     ones
    0.96
    those
    0.96
    它们
    0.93
    Those
    0.86
    Activations Density 0.977%

    No Known Activations