© 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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3272
    Prev
    Next
    INDEX
    Explanations

    references to significant locations or entities, particularly related to political or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forChild
    -0.57
    tableFuture
    -0.53
    addGap
    -0.48
    terung
    -0.48
    PDOException
    -0.46
    StyleSheet
    -0.45
    بوابة
    -0.45
    érience
    -0.44
    cemment
    -0.44
     Longfellow
    -0.43
    POSITIVE LOGITS
     with
    1.08
     WITH
    1.05
    WITH
    1.02
    with
    0.99
     With
    0.99
     avec
    0.95
    With
    0.90
    avec
    0.86
    dengan
    0.85
    Avec
    0.84
    Activations Density 0.376%

    No Known Activations