© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15477
    Prev
    Next
    INDEX
    Explanations

    the concept of contemplating or reflecting on past experiences and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parac
    -0.76
     كومونز
    -0.64
     ThemeData
    -0.60
     NgModule
    -0.60
    ercito
    -0.59
    fendi
    -0.59
     esternos
    -0.58
    expandindo
    -0.58
     hini
    -0.57
    ageo
    -0.56
    POSITIVE LOGITS
     thinking
    1.26
     think
    1.25
     thought
    1.20
     THINK
    1.19
     Think
    1.14
     Thinking
    1.11
     thoughts
    1.10
    thinking
    1.09
    Thinking
    1.08
    thought
    1.06
    Activations Density 0.148%

    No Known Activations