© 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. 40-GEMMASCOPE-RES-16K
    11. 1504
    Prev
    Next
    INDEX
    Explanations

    phrases related to gratitude and acknowledgment of contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::_('
    -0.48
    ötzlich
    -0.43
    galus
    -0.41
    IntoConstraints
    -0.40
    isesi
    -0.39
    letoe
    -0.39
    ürlich
    -0.39
    SerializedSize
    -0.38
     ſtate
    -0.38
    OrEqual
    -0.38
    POSITIVE LOGITS
     without
    3.94
    without
    3.38
     Without
    3.23
    Without
    3.19
     ohne
    2.91
     zonder
    2.89
     без
    2.86
     WITHOUT
    2.86
     tanpa
    2.86
     ilman
    2.70
    Activations Density 1.938%

    No Known Activations