© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1250
    Prev
    Next
    INDEX
    Explanations

    tokens related to observing experiences and emotions

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

    Follows a verb of perception or action

    np_acts-logits-general · gemini-2.0-flash

    or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -0.68
     reaſon
    -0.66
     pleaſure
    -0.64
     ſtill
    -0.63
     ſaid
    -0.62
     ſtate
    -0.60
     purpoſe
    -0.60
    findIndex
    -0.59
     ſtre
    -0.58
     سكانية
    -0.58
    POSITIVE LOGITS
     anymore
    1.60
     nor
    1.14
     any
    1.03
     necessarily
    0.97
     nenhuma
    0.94
     żad
    0.89
     nicio
    0.89
     yet
    0.87
     sondern
    0.85
     nenhum
    0.84
    Activations Density 0.649%

    No Known Activations