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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8348
    Prev
    Next
    INDEX
    Explanations

    expressions and discussions related to personal beliefs and opinions

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

    references to personal viewpoints and ideological stances, especially meta-statements about expressing, publishing, or disclaiming opinions

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "opinion" or "opinions", particularly in contexts discussing personal views or beliefs.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chränk
    -0.65
    oa̍t
    -0.62
    }*/
    -0.52
    الإنجليزية
    -0.52
     OGS
    -0.50
    :✨
    -0.50
     Himalayas
    -0.50
    ſelves
    -0.49
     ſch
    -0.49
    ſelf
    -0.49
    POSITIVE LOGITS
     opinion
    1.24
     opinions
    1.16
    opinion
    1.07
     opinión
    1.04
     Opinion
    1.03
     Opinions
    1.02
    Opinion
    0.98
     opinião
    0.97
    Opinions
    0.96
     Meinung
    0.94
    Activations Density 0.235%

    No Known Activations