© 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. 5415
    Prev
    Next
    INDEX
    Explanations

    Java annotations and ORM (Object-Relational Mapping) terminology

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

    Java code structures

    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
    SequentialGroup
    -0.81
    :✨
    -0.75
    gameserver
    -0.59
    mybatisplus
    -0.57
    ThroughAttribute
    -0.56
     AssemblyCompany
    -0.55
     sää
    -0.55
    ſſung
    -0.54
    +#+#
    -0.54
    bibfield
    -0.53
    POSITIVE LOGITS
    numerusform
    0.40
     pom
    0.29
     ale
    0.28
    rrggbb
    0.27
    geord
    0.27
    Oid
    0.27
     bru
    0.26
     ly
    0.26
     exercise
    0.25
     nam
    0.25
    Activations Density 0.003%

    No Known Activations