© 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. 23-GEMMASCOPE-RES-16K
    11. 1997
    Prev
    Next
    INDEX
    Explanations

    chronological markers and temporal phrases within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     was
    -0.41
     mixture
    -0.36
     roller
    -0.36
     mont
    -0.34
     alone
    -0.33
    IUrlHelper
    -0.33
    之间
    -0.33
    subsubsection
    -0.32
     (%
    -0.32
     program
    -0.32
    POSITIVE LOGITS
    writeField
    0.79
     noDo
    0.63
    帖最后由
    0.62
    aronder
    0.60
     transférez
    0.59
    ніципалі
    0.56
    AndEndTag
    0.54
    Välislingid
    0.54
    原始内容存档于
    0.54
    četně
    0.53
    Activations Density 0.611%

    No Known Activations