© 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. 3-GEMMASCOPE-RES-16K
    11. 15922
    Prev
    Next
    INDEX
    Explanations

    instances of the word "think" and variations of expressing opinion or thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.63
    ,
    -0.57
    øya
    -0.57
     so
    -0.52
     ca
    -0.49
    أن
    -0.49
    <strong>
    -0.49
    :
    -0.48
     an
    -0.47
     (
    -0.47
    POSITIVE LOGITS
    aarrggbb
    1.18
     itſelf
    1.15
     Efq
    1.06
     Jefus
    1.05
     myſelf
    1.04
     themſelves
    1.04
     Monfieur
    1.04
     estekak
    1.03
     Shakspeare
    0.99
     ―――――
    0.97
    Activations Density 0.106%

    No Known Activations