© 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. 28-GEMMASCOPE-RES-16K
    11. 7848
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to specific durations or time-related elements in contexts like studies or contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding ampersands, commas, or periods

    np_acts-logits-general · gemini-2.0-flash

    long-lived and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    しばらく
    -0.55
     lasted
    -0.54
     longstanding
    -0.53
     lasts
    -0.52
     لمدة
    -0.50
     lifelong
    -0.50
    短短
    -0.47
     longtime
    -0.46
     lasting
    -0.44
     spend
    -0.42
    POSITIVE LOGITS
     AssemblyCulture
    0.71
     AssemblyProduct
    0.66
     OMITBAD
    0.59
    parsedMessage
    0.59
    
    0.58
    AndEndTag
    0.58
    CDCl
    0.57
     pleaſure
    0.56
     CreateTagHelper
    0.55
    ^(@)
    0.55
    Activations Density 0.712%

    No Known Activations