© 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. 2-GEMMASCOPE-RES-16K
    11. 8445
    Prev
    Next
    INDEX
    Explanations

    frequency of the word "another" and similar variations indicating continuation or repetition in context

    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
     للمعارف
    -0.82
     للاسماء
    -0.74
    Билгалдахарш
    -0.72
    rawDesc
    -0.69
    WriteTagHelper
    -0.68
    
    -0.67
    CppMethod
    -0.67
     témoig
    -0.65
    parsedMessage
    -0.64
    argout
    -0.63
    POSITIVE LOGITS
    <bos>
    0.43
    still
    0.36
    Still
    0.29
    }\
    0.28
    M
    0.27
     содержания
    0.27
    Int
    0.27
    STILL
    0.26
    boldsymbol
    0.26
    original
    0.26
    Activations Density 0.090%

    No Known Activations