© 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. 21-GEMMASCOPE-RES-16K
    11. 1161
    Prev
    Next
    INDEX
    Explanations

    keywords related to high-stakes situations or intense emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -1.32
    ,
    -0.92
    .
    -0.84
     a
    -0.81
    :
    -0.81
     O
    -0.79
     I
    -0.78
     in
    -0.78
     E
    -0.77
     H
    -0.77
    POSITIVE LOGITS
     itſelf
    1.54
     ་་
    1.25
     للمعارف
    1.25
     photolibrary
    1.19
     myſelf
    1.16
     doubtnut
    1.15
     raiſ
    1.15
     Majefty
    1.14
     $_"
    1.14
    tvguidetime
    1.13
    Activations Density 0.579%

    No Known Activations