© 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. 16231
    Prev
    Next
    INDEX
    Explanations

    phrases related to convenience and user-friendly features

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

    following "for" implying ease or safety

    np_acts-logits-general · gemini-2.0-flash

    for, followed by positive descriptors

    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
    guien
    -0.50
     JpaRepository
    -0.49
     nhiêu
    -0.48
    하다
    -0.45
     cref
    -0.44
     ceea
    -0.44
    principalColumn
    -0.43
    exists
    -0.42
    そもそも
    -0.41
    зно
    -0.40
    POSITIVE LOGITS
     easier
    1.34
     easy
    1.24
     ease
    1.15
    Easier
    1.14
    easier
    1.11
     easiest
    1.09
     optimal
    1.04
     Easier
    1.00
    easy
    0.99
     convenience
    0.97
    Activations Density 0.219%

    No Known Activations