© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14946
    Prev
    Next
    INDEX
    Explanations

    technical references and specifications related to programming or software configurations

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

    Follows "note", "question", or "reference"

    np_acts-logits-general · gemini-2.0-flash

    question and reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    principalColumn
    -0.81
     StyleSheet
    -0.61
    ReusableCell
    -0.58
    Portale
    -0.55
    PerformLayout
    -0.55
     doInBackground
    -0.54
     Савезне
    -0.53
     typelib
    -0.52
     restTemplate
    -0.51
     autorytatywna
    -0.51
    POSITIVE LOGITS
     note
    1.06
     Note
    1.05
    Note
    0.90
    note
    0.83
     NOTE
    0.81
     optionally
    0.74
     notice
    0.70
    NOTE
    0.69
     Alternatively
    0.69
     Use
    0.68
    Activations Density 0.701%

    No Known Activations