© 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. 15112
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that indicate naming or categorization

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

    Preceding a term or name

    np_acts-logits-general · gemini-2.0-flash

    is called or termed

    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
     سكانية
    -0.65
    ValueStyle
    -0.65
    aucune
    -0.59
     XNUMX
    -0.59
     OGS
    -0.59
    autres
    -0.58
     comets
    -0.58
    évaluateur
    -0.57
     Hopf
    -0.57
     Hege
    -0.57
    POSITIVE LOGITS
     “
    1.28
     "
    1.24
     ‘
    1.08
     simply
    0.97
     «
    0.96
     '
    0.94
     „
    0.92
     `
    0.83
     ”
    0.83
    之为
    0.81
    Activations Density 0.170%

    No Known Activations