© 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. 15096
    Prev
    Next
    INDEX
    Explanations

    names of publishers and their associated works or events

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

    after publishers or presses

    np_acts-logits-general · gemini-2.0-flash

    publisher names

    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
    AllowUser
    -0.58
    AutoSize
    -0.52
    ngOnInit
    -0.48
    giaan
    -0.48
     esterni
    -0.46
    stdc
    -0.46
     attends
    -0.44
     soie
    -0.44
    QObject
    -0.44
    TargetApi
    -0.43
    POSITIVE LOGITS
     Press
    0.96
     publisher
    0.95
     press
    0.92
    Press
    0.91
     publishing
    0.88
     publishers
    0.87
     presses
    0.87
    press
    0.85
    PRESS
    0.81
     Presses
    0.80
    Activations Density 0.180%

    No Known Activations