© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 97457
    Prev
    Next
    INDEX
    Explanations

    the name "Ja" in various formats

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

    Ja followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eschou
    -0.52
    unnitel
    -0.50
    voř
    -0.49
    mtr
    -0.47
     oner
    -0.47
    ":{"
    -0.46
    cshtml
    -0.45
    انجليز
    -0.45
    refront
    -0.44
    ésult
    -0.44
    POSITIVE LOGITS
     Ja
    2.17
    Ja
    2.02
     ja
    1.45
     JA
    1.42
     Jaffe
    1.38
    JA
    1.20
    ja
    1.06
     Jai
    0.84
     Jae
    0.82
    Jae
    0.79
    Activations Density 0.007%

    No Known Activations