© 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. 27-GEMMASCOPE-RES-16K
    6. 9956
    Prev
    Next
    INDEX
    Explanations

    topics related to geopolitical conflict and sanctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.62
     rhestr
    -0.58
     houſe
    -0.57
     fubject
    -0.56
     Reſ
    -0.55
     Diſ
    -0.53
    fitrión
    -0.50
     Majefty
    -0.50
     CreateTagHelper
    -0.49
    出版年
    -0.49
    POSITIVE LOGITS
    saraba
    0.34
    (!__
    0.32
    httphttps
    0.31
     Sochi
    0.31
     Assad
    0.30
     Maduro
    0.30
     те
    0.30
     Сочи
    0.30
     ogóle
    0.29
     Putin
    0.29
    Activations Density 0.178%

    No Known Activations