© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 82706
    Prev
    Next
    INDEX
    Explanations

    references to diaries and diary entries

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

    diary

    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
     Schne
    -0.44
     Mun
    -0.43
     masculin
    -0.42
    Steffen
    -0.41
    Mun
    -0.41
    n
    -0.41
     מן
    -0.40
    sen
    -0.40
     Black
    -0.39
    xC
    -0.39
    POSITIVE LOGITS
     diary
    2.16
     Diary
    2.14
    Diary
    1.97
     diaries
    1.76
    diary
    1.73
     Diaries
    1.59
    日记
    0.98
     diário
    0.94
    Diario
    0.94
    日記
    0.90
    Activations Density 0.005%

    No Known Activations