© 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. 4476
    Prev
    Next
    INDEX
    Explanations

    phrases that express thoughts, opinions, or realizations

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

    phrases expressing reflective thoughts or introspective moments, particularly those starting with "I thought".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    BagConstraints
    -0.68
     nakalista
    -0.66
    estacks
    -0.65
     صوتيه
    -0.63
    الإنجليزية
    -0.63
     snippetHide
    -0.62
    rrggbb
    -0.61
     مشين
    -0.59
     queſta
    -0.58
     StringTokenizer
    -0.58
    POSITIVE LOGITS
     thought
    0.74
     Thought
    0.58
    Thought
    0.51
    thought
    0.50
     hoped
    0.50
     THOUGHT
    0.45
     supposed
    0.44
     tưởng
    0.44
     думал
    0.43
     think
    0.41
    Activations Density 0.086%

    No Known Activations