© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 16037
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and responses, particularly focusing on the verb "ran" and answers to questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Aholisi
    -0.71
    Personendaten
    -0.58
     Roskov
    -0.56
    Demografie
    -0.54
    exitRule
    -0.54
    AsStream
    -0.53
    writeFieldEnd
    -0.51
    StatusOK
    -0.51
     دیکھیے
    -0.50
     ब्रेकडाउन
    -0.50
    POSITIVE LOGITS
     answered
    0.56
    Ran
    0.46
    answered
    0.44
     Answered
    0.40
     believer
    0.39
    asso
    0.38
    Continue
    0.38
    Mae
    0.38
    Installation
    0.37
     ran
    0.37
    Activations Density 0.069%

    No Known Activations