© 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. 33-GEMMASCOPE-RES-16K
    6. 7700
    Prev
    Next
    INDEX
    Explanations

    SQL commands related to ordering and sorting data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.75
    httphttps
    -0.72
     snippetHide
    -0.64
    Ārējās
    -0.57
    ButterKnife
    -0.56
     للمعارف
    -0.56
     informée
    -0.54
     CreateTagHelper
    -0.51
    ReusableCell
    -0.50
     betweenstory
    -0.50
    POSITIVE LOGITS
     ascending
    1.20
     descending
    1.12
     asc
    1.03
     Asc
    1.01
     desc
    0.97
    ascending
    0.96
     ascend
    0.94
    asc
    0.93
    Ascending
    0.91
     Desc
    0.90
    Activations Density 0.204%

    No Known Activations