© 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. 4311
    Prev
    Next
    INDEX
    Explanations

    phrases related to contingency plans and backup systems

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

    Contingency, back-up, and alternative plans

    np_acts-logits-general · gemini-2.0-flash

    backup contingency fallback plans

    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
    PerformLayout
    -0.78
    elemField
    -0.76
    InputBorder
    -0.71
    providedIn
    -0.65
    évaluateur
    -0.65
    ]")]
    -0.63
     TextInputType
    -0.62
    DropColumn
    -0.59
    MergeFrom
    -0.57
    EndInit
    -0.57
    POSITIVE LOGITS
     backup
    1.70
     emergency
    1.52
     fallback
    1.50
     contingency
    1.46
     Backup
    1.36
    backup
    1.34
    emergency
    1.32
     backups
    1.31
     alternative
    1.31
     alternate
    1.30
    Activations Density 0.296%

    No Known Activations