© 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. 31-GEMMASCOPE-RES-16K
    11. 11689
    Prev
    Next
    INDEX
    Explanations

    words related to misconceptions and public perception

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

    phrases that express deliberate deception or misleading of people.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.51
    うーん
    -0.45
     Baw
    -0.36
     endblock
    -0.36
     Dall
    -0.35
     ma
    -0.35
     MA
    -0.35
    ällig
    -0.35
    无力
    -0.34
     FIND
    -0.32
    POSITIVE LOGITS
    以為
    1.72
    以为
    1.66
     believing
    1.60
     mistakenly
    1.45
     mistaken
    1.42
     believed
    1.41
     croire
    1.30
     misconception
    1.30
     thought
    1.27
     belief
    1.27
    Activations Density 0.590%

    No Known Activations