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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16154
    Prev
    Next
    INDEX
    Explanations

    specific non-English characters and words

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

    non-English characters and scripts from various languages (Arabic, Korean, Thai, Croatian, etc.).

    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
    +:+
    -0.37
     certamen
    -0.31
     kimi
    -0.28
    krim
    -0.27
     Sambo
    -0.25
     frit
    -0.25
     dziennik
    -0.24
     mena
    -0.24
    ジラ
    -0.24
    랑
    -0.24
    POSITIVE LOGITS
    AddTagHelper
    0.76
    SharedCtor
    0.73
     EconPapers
    0.72
    httphttps
    0.61
    ніципалі
    0.60
    ыгана
    0.60
    رشف
    0.60
     betweenstory
    0.60
     unknownFields
    0.59
     CURIAM
    0.59
    Activations Density 0.040%

    No Known Activations