© 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. 18-GEMMASCOPE-RES-16K
    11. 9834
    Prev
    Next
    INDEX
    Explanations

    elements related to plot twists and endings in narratives

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

    conclusions and outcomes

    np_acts-logits-general · gemini-2.0-flash

    story endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.65
     հղումներ
    -0.59
     propOrder
    -0.55
    ergies
    -0.54
    tvguidetime
    -0.53
    IBar
    -0.53
    ngdoc
    -0.52
    keyColumn
    -0.51
    AccessorTable
    -0.51
    Rè
    -0.51
    POSITIVE LOGITS
     ending
    1.64
     endings
    1.46
     outcome
    1.31
     Ending
    1.29
    Ending
    1.12
    ending
    1.06
    outcome
    1.06
     Outcome
    1.05
     outcomes
    1.05
    结局
    1.02
    Activations Density 0.194%

    No Known Activations