© 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. 11369
    Prev
    Next
    INDEX
    Explanations

    expressions related to self-reflection and personal conclusions

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

    the beginning of sentences or clauses with first-person pronouns and auxiliary verbs.

    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
    ьаж
    -0.60
     defaultstate
    -0.60
     يتيمه
    -0.54
    optionalTypeArgs
    -0.53
    Хьажоргаш
    -0.53
     cioè
    -0.53
    ibatkan
    -0.51
    SharedCtor
    -0.49
    utuhkan
    -0.48
     anzi
    -0.47
    POSITIVE LOGITS
     Wikiseite
    0.62
    以上就是
    0.58
     digress
    0.56
     natomiast
    0.52
    Another
    0.52
     wikipagina
    0.52
     infine
    0.51
    withstanding
    0.51
     übrigens
    0.50
    另一個
    0.50
    Activations Density 0.787%

    No Known Activations