© 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. 10986
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically quotation marks and commas

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

    Quoted speech

    np_acts-logits-general · gemini-2.0-flash

    closing quotes and speech verbs

    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
     ddelweddau
    -0.68
    UrlResolution
    -0.55
    pulumi
    -0.51
    spiller
    -0.51
    LLocation
    -0.48
    SizeMode
    -0.48
    beforeSend
    -0.47
    IUrlHelper
    -0.47
     ivelany
    -0.45
    espèce
    -0.45
    POSITIVE LOGITS
     said
    1.17
     says
    0.97
    said
    0.95
    says
    0.84
    ]")]
    0.80
     ""],
    0.80
     <=",
    0.78
    $")
    0.74
     gezegd
    0.73
    httphttps
    0.73
    Activations Density 0.033%

    No Known Activations