© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12564
    Prev
    Next
    INDEX
    Explanations

    words related to evaluations of actions and their justifications

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

    Positive sentiment relating to past events

    np_acts-logits-general · gemini-2.0-flash

    past tense evaluations

    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
     currently
    -1.14
    currently
    -1.11
     derzeit
    -1.05
     presently
    -0.98
     tomorrow
    -0.97
     now
    -0.96
     attualmente
    -0.92
    Currently
    -0.91
     Currently
    -0.89
     actuellement
    -0.89
    POSITIVE LOGITS
     was
    1.18
     wasn
    1.07
     didn
    1.03
     did
    1.02
     damals
    0.98
    Wasn
    0.97
     toen
    0.95
     ayer
    0.95
    was
    0.94
     originally
    0.93
    Activations Density 2.042%

    No Known Activations