© 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. 2-GEMMASCOPE-RES-16K
    11. 13510
    Prev
    Next
    INDEX
    Explanations

    phrases related to composition or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.41
     computers
    -0.39
     tomorrow
    -0.39
     stressed
    -0.36
     Tomorrow
    -0.35
    Tomorrow
    -0.35
     unemployment
    -0.35
     téléchargez
    -0.35
    Koordin
    -0.34
    usermodel
    -0.34
    POSITIVE LOGITS
     consisting
    1.06
     consist
    0.94
     consisted
    0.94
     composed
    0.88
     consists
    0.86
    composed
    0.78
     Composed
    0.76
     comprised
    0.73
     composta
    0.71
     består
    0.69
    Activations Density 0.139%

    No Known Activations