© 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. 16095
    Prev
    Next
    INDEX
    Explanations

    references to sound or auditory experiences

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

    ending in "er."

    np_acts-logits-general · gemini-2.0-flash

    words ending in er or ter

    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
     CommonModule
    -0.87
    scriptcase
    -0.79
    skosten
    -0.78
    chitis
    -0.78
     MenuView
    -0.77
    躇
    -0.76
     BoxFit
    -0.75
    swick
    -0.75
    skraft
    -0.72
    السكان
    -0.72
    POSITIVE LOGITS
    er
    1.37
    ed
    0.94
    ER
    0.92
    ized
    0.87
    nder
    0.84
    ization
    0.78
    ised
    0.77
    ber
    0.76
    ه
    0.75
    iver
    0.71
    Activations Density 0.907%

    No Known Activations