© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 948
    Prev
    Next
    INDEX
    Explanations

    references to historical or political figures and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quizá
    -0.40
     vů
    -0.39
    desenho
    -0.37
     labores
    -0.35
     pudieran
    -0.35
     rodillas
    -0.34
     Pflichten
    -0.34
     Auftritt
    -0.34
     hacerle
    -0.34
     Landwirtschaft
    -0.33
    POSITIVE LOGITS
    SourceChecksum
    1.03
     autorytatywna
    1.02
     surla
    0.97
     queſta
    0.94
    iſchen
    0.93
     ſei
    0.91
    脚注の使い方
    0.90
     beſte
    0.88
    存于互联网档案馆
    0.88
    iſche
    0.88
    Activations Density 0.078%

    No Known Activations