© 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. 38-GEMMASCOPE-RES-16K
    11. 7771
    Prev
    Next
    INDEX
    Explanations

    time-related phrases signifying duration or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Days
    -0.50
     TType
    -0.45
     imageNamed
    -0.45
    Days
    -0.43
    NameInMap
    -0.41
    שרה
    -0.39
    Hours
    -0.37
    ApiModelProperty
    -0.36
    PageInfo
    -0.36
    styleUrls
    -0.35
    POSITIVE LOGITS
     decade
    1.74
     decades
    1.65
    decade
    1.46
     décadas
    1.33
     década
    1.31
     Decade
    1.22
     décennies
    1.20
    十年
    0.95
     thập
    0.95
     years
    0.90
    Activations Density 0.262%

    No Known Activations