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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 15760
    Prev
    Next
    INDEX
    Explanations

    expressions related to thinking or thoughts

    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
     osmosis
    -0.51
     dated
    -0.47
    ogaster
    -0.47
     resourceCulture
    -0.46
     daly
    -0.45
    Fam
    -0.44
     defaultstate
    -0.43
     Record
    -0.43
    Record
    -0.43
    essentiel
    -0.43
    POSITIVE LOGITS
     hoped
    0.81
    Lähteet
    0.71
    RectangleBorder
    0.69
     mergeFrom
    0.66
     GenerationType
    0.60
     оригіналу
    0.59
     بيها
    0.59
    illoma
    0.58
    SequentialGroup
    0.57
    vernight
    0.56
    Activations Density 0.410%

    No Known Activations