© 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. 53635
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations and the term "dealloc" related to memory management in programming

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

    radical scavenging activity

    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
    IntoConstraints
    -0.66
    Autoritní
    -0.50
    protoimpl
    -0.49
    
    -0.49
     referrerpolicy
    -0.46
     فريبيس
    -0.46
     민
    -0.45
    ModelSerializer
    -0.45
    __':
    -0.44
     JpaRepository
    -0.43
    POSITIVE LOGITS
    yang
    2.06
    阳
    0.93
    陽
    0.83
     Chico
    0.82
    anyang
    0.77
    ongyang
    0.75
    Chico
    0.74
    oyang
    0.73
     yang
    0.71
     YANG
    0.65
    Activations Density 0.002%

    No Known Activations