© 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. 39-GEMMASCOPE-RES-16K
    11. 4099
    Prev
    Next
    INDEX
    Explanations

    closing braces or curly brace symbols in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    的
    -2.09
    の
    -2.05
    의
    -1.23
    ها
    -1.10
    的角度
    -0.99
    的她
    -0.98
    のようです
    -0.94
    のほうが
    -0.92
    のサ
    -0.91
    的公司
    -0.88
    POSITIVE LOGITS
    OOO
    0.59
    aaa
    0.40
     Jornada
    0.38
    ारी
    0.36
     Egan
    0.35
     parrilla
    0.35
     Syrie
    0.35
    "");
    0.35
    aat
    0.34
    acterium
    0.34
    Activations Density 0.512%

    No Known Activations