© 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. 107520
    Prev
    Next
    INDEX
    Explanations

    repeated references to the concept of "core" as it relates to central themes or attributes

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

    core and its attributes

    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
    rollment
    -0.50
     tartalomajánló
    -0.46
    cember
    -0.42
     XXL
    -0.42
    ScopeManager
    -0.41
     Yandex
    -0.40
     gof
    -0.40
     Transfermarkt
    -0.39
     pesta
    -0.39
     mister
    -0.39
    POSITIVE LOGITS
     core
    1.84
     Core
    1.54
    Core
    1.48
    core
    1.41
     CORE
    1.34
    核心
    1.27
    CORE
    1.16
    的核心
    1.12
    コア
    1.00
     cores
    0.93
    Activations Density 0.008%

    No Known Activations