© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16127
    Prev
    Next
    INDEX
    Explanations

    the word "Another" and its variations, indicating a focus on reiteration or addition in the context of the text

    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
     balení
    -0.68
     saiba
    -0.64
     tarko
    -0.62
     öv
    -0.60
     increí
    -0.59
     høre
    -0.57
     aikana
    -0.57
     mukana
    -0.57
     picioare
    -0.57
     ſind
    -0.56
    POSITIVE LOGITS
     another
    2.64
    another
    2.41
    Another
    2.20
     Another
    2.20
     ANOTHER
    2.00
    另一个
    1.41
    Otra
    1.37
     otra
    1.36
     otro
    1.34
     Otra
    1.33
    Activations Density 0.077%

    No Known Activations