© 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. 4-GEMMASCOPE-RES-16K
    6. 9346
    Prev
    Next
    INDEX
    Explanations

    terms related to ruining or spoiling experiences or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     places
    -0.48
    CODEC
    -0.47
    mobileqq
    -0.47
    เงิน
    -0.46
     Apel
    -0.45
     correct
    -0.45
     V
    -0.45
    places
    -0.45
     strange
    -0.44
    állítás
    -0.44
    POSITIVE LOGITS
     spoiling
    1.21
     ruining
    1.19
     ruined
    1.09
     spoil
    1.06
     spoilt
    1.03
     spoiled
    1.02
     ruin
    1.01
    GEBURTSDATUM
    0.97
    abestanden
    0.90
     spoils
    0.86
    Activations Density 0.339%

    No Known Activations