© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 875
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing processes or activities

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

    followed by "to"

    np_acts-logits-general · gemini-2.0-flash

    previously or before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.54
    ngrx
    -0.48
    GraphicsUnit
    -0.47
     resourceCulture
    -0.44
     IconData
    -0.39
    Coordonnées
    -0.38
    createStatement
    -0.38
    DataPropertyName
    -0.38
    pertino
    -0.37
     pageNum
    -0.37
    POSITIVE LOGITS
     auparavant
    0.65
    Previously
    0.60
     Previously
    0.60
     previously
    0.59
    previously
    0.56
     tidligere
    0.54
     anteriormente
    0.54
     tidigare
    0.53
     wcześniej
    0.51
     ранее
    0.48
    Activations Density 0.867%

    No Known Activations