© 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. 12799
    Prev
    Next
    INDEX
    Explanations

    verbs indicating successful actions or achievements

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

    managed to achieve

    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
     lookout
    -0.38
    poxy
    -0.36
    Enums
    -0.35
    ols
    -0.35
    OLS
    -0.34
    JComboBox
    -0.34
     tailor
    -0.34
     VOL
    -0.33
    setView
    -0.33
     lawn
    -0.32
    POSITIVE LOGITS
     riuscito
    1.09
     riesce
    1.05
     conseguiu
    1.04
     riusc
    1.02
     réussi
    0.98
     geschafft
    0.96
     réussir
    0.95
     berhasil
    0.95
     rius
    0.94
     consegue
    0.94
    Activations Density 0.029%

    No Known Activations