© 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. 23-GEMMASCOPE-RES-16K
    11. 9088
    Prev
    Next
    INDEX
    Explanations

    references to specific legal cases and environmental regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.51
    ፩
    -0.51
    __':
    -0.49
     noDo
    -0.49
     nakalista
    -0.48
    يكب
    -0.48
     NUKAT
    -0.47
    imageshack
    -0.47
    ніципа
    -0.47
    jini
    -0.47
    POSITIVE LOGITS
     @"/
    0.45
    Personensuche
    0.38
    ArrowToggle
    0.35
    lottesville
    0.35
    Vietnam
    0.35
     Vietnam
    0.34
     Vietnamese
    0.33
    tagext
    0.33
     Saigon
    0.33
     CreateTagHelper
    0.32
    Activations Density 0.786%

    No Known Activations