© 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. 7-GEMMASCOPE-RES-16K
    11. 16030
    Prev
    Next
    INDEX
    Explanations

    instances of the word "every" and its variations, indicating a focus on concepts related to universality or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brunch
    -0.42
     Scale
    -0.40
     Brandt
    -0.38
     Jiao
    -0.37
     Oboe
    -0.36
    いろいろ
    -0.36
    textArea
    -0.36
    ण्ड
    -0.36
     Suggestion
    -0.35
     Liaison
    -0.35
    POSITIVE LOGITS
     every
    2.44
    every
    2.39
    Every
    2.27
     Every
    2.25
     EVERY
    1.97
    EVERY
    1.79
     setiap
    1.55
     ogni
    1.51
    Ogni
    1.48
    Setiap
    1.38
    Activations Density 0.077%

    No Known Activations